prosemble 2.2.0__tar.gz → 2.4.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (328) hide show
  1. {prosemble-2.2.0 → prosemble-2.4.0}/PKG-INFO +1 -1
  2. {prosemble-2.2.0 → prosemble-2.4.0}/nix/package.nix +9 -8
  3. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/__init__.py +25 -0
  4. prosemble-2.4.0/prosemble/core/curriculum.py +171 -0
  5. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/distance.py +183 -0
  6. prosemble-2.4.0/prosemble/core/geodesic.py +217 -0
  7. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/manifolds.py +166 -0
  8. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/onnx_export.py +146 -3
  9. prosemble-2.4.0/prosemble/core/optimizers.py +292 -0
  10. prosemble-2.4.0/prosemble/core/regularization.py +210 -0
  11. prosemble-2.4.0/prosemble/core/reject.py +246 -0
  12. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/__init__.py +47 -2
  13. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/celvq_ng_mixin.py +11 -3
  14. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_glvq.py +5 -0
  15. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_glvq_ng.py +22 -2
  16. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_matrix_lvq.py +4 -0
  17. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_matrix_lvq_ng.py +21 -2
  18. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_relevance_lvq.py +6 -0
  19. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_relevance_lvq_ng.py +23 -2
  20. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/local_matrix_lvq.py +6 -0
  21. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/matrix_lvq.py +6 -0
  22. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/mrslvq_ng.py +18 -6
  23. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_glvq.py +8 -6
  24. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_matrix_lvq.py +5 -4
  25. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_relevance_lvq.py +5 -4
  26. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_glvq.py +56 -9
  27. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_glvq_ng_mixin.py +10 -2
  28. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_gmlvq.py +20 -2
  29. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_grlvq.py +15 -4
  30. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_gtlvq.py +15 -2
  31. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_lgmlvq.py +22 -2
  32. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_mrslvq.py +9 -5
  33. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_rslvq.py +1 -1
  34. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_rslvq_ng_mixin.py +10 -4
  35. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/prototype_base.py +2 -1
  36. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/relevance_lvq.py +5 -0
  37. prosemble-2.4.0/prosemble/models/riemannian_dk_glvq.py +315 -0
  38. prosemble-2.4.0/prosemble/models/riemannian_dk_m_slng.py +314 -0
  39. prosemble-2.4.0/prosemble/models/riemannian_dk_m_smng.py +314 -0
  40. prosemble-2.4.0/prosemble/models/riemannian_dk_m_stng.py +318 -0
  41. prosemble-2.4.0/prosemble/models/riemannian_dk_matrix_lvq.py +350 -0
  42. prosemble-2.4.0/prosemble/models/riemannian_dk_r_slng.py +363 -0
  43. prosemble-2.4.0/prosemble/models/riemannian_dk_r_smng.py +364 -0
  44. prosemble-2.4.0/prosemble/models/riemannian_dk_r_stng.py +370 -0
  45. prosemble-2.4.0/prosemble/models/riemannian_dk_relevance_lvq.py +387 -0
  46. prosemble-2.4.0/prosemble/models/riemannian_dk_slng.py +330 -0
  47. prosemble-2.4.0/prosemble/models/riemannian_dk_smng.py +330 -0
  48. prosemble-2.4.0/prosemble/models/riemannian_dk_stng.py +339 -0
  49. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/riemannian_neural_gas.py +6 -1
  50. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/riemannian_slng.py +10 -2
  51. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/riemannian_smng.py +15 -3
  52. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/riemannian_srng.py +100 -5
  53. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/riemannian_stng.py +11 -2
  54. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/rslvq_ng.py +9 -3
  55. prosemble-2.4.0/prosemble/models/scmng.py +289 -0
  56. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/slng.py +17 -2
  57. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/smng.py +17 -2
  58. prosemble-2.4.0/prosemble/models/sng.py +259 -0
  59. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/srng.py +18 -2
  60. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/stng.py +17 -2
  61. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/svq_occ.py +2 -2
  62. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/tangent_lvq.py +8 -0
  63. prosemble-2.4.0/prosemble/models/wasserstein_glvq.py +231 -0
  64. prosemble-2.4.0/prosemble/models/wasserstein_gmlvq.py +270 -0
  65. prosemble-2.4.0/prosemble/models/wasserstein_grlvq.py +259 -0
  66. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble.egg-info/PKG-INFO +1 -1
  67. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble.egg-info/SOURCES.txt +30 -1
  68. {prosemble-2.2.0 → prosemble-2.4.0}/pyproject.toml +1 -1
  69. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/api/core.rst +35 -0
  70. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/api/models.rst +59 -0
  71. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/conf.py +1 -1
  72. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/advanced.rst +262 -0
  73. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/differentiating_kernels.rst +74 -0
  74. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/onnx.rst +56 -2
  75. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/riemannian.rst +91 -2
  76. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/supervised.rst +147 -2
  77. prosemble-2.4.0/tests/test_hyperbolic.py +292 -0
  78. prosemble-2.4.0/tests/test_improvements.py +703 -0
  79. prosemble-2.4.0/tests/test_ng_lr_ratio.py +153 -0
  80. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_onnx_export.py +90 -0
  81. prosemble-2.4.0/tests/test_riemannian_dk_models.py +1043 -0
  82. prosemble-2.4.0/tests/test_scmng.py +258 -0
  83. prosemble-2.4.0/tests/test_sng.py +225 -0
  84. prosemble-2.4.0/tests/test_wasserstein.py +302 -0
  85. {prosemble-2.2.0 → prosemble-2.4.0}/uv.lock +201 -207
  86. {prosemble-2.2.0 → prosemble-2.4.0}/.bumpversion.cfg +0 -0
  87. {prosemble-2.2.0 → prosemble-2.4.0}/.editorconfig +0 -0
  88. {prosemble-2.2.0 → prosemble-2.4.0}/.envrc +0 -0
  89. {prosemble-2.2.0 → prosemble-2.4.0}/.github/ISSUE_TEMPLATE/bug_report.md +0 -0
  90. {prosemble-2.2.0 → prosemble-2.4.0}/.github/ISSUE_TEMPLATE/config.yml +0 -0
  91. {prosemble-2.2.0 → prosemble-2.4.0}/.github/ISSUE_TEMPLATE/feature_request.md +0 -0
  92. {prosemble-2.2.0 → prosemble-2.4.0}/.github/workflows/ci.yml +0 -0
  93. {prosemble-2.2.0 → prosemble-2.4.0}/.github/workflows/release.yml +0 -0
  94. {prosemble-2.2.0 → prosemble-2.4.0}/.gitignore +0 -0
  95. {prosemble-2.2.0 → prosemble-2.4.0}/.readthedocs.yaml +0 -0
  96. {prosemble-2.2.0 → prosemble-2.4.0}/CONSTITUTION.md +0 -0
  97. {prosemble-2.2.0 → prosemble-2.4.0}/LICENSE +0 -0
  98. {prosemble-2.2.0 → prosemble-2.4.0}/MANIFEST.in +0 -0
  99. {prosemble-2.2.0 → prosemble-2.4.0}/ONNX_COVERAGE.md +0 -0
  100. {prosemble-2.2.0 → prosemble-2.4.0}/README.md +0 -0
  101. {prosemble-2.2.0 → prosemble-2.4.0}/TASK.md +0 -0
  102. {prosemble-2.2.0 → prosemble-2.4.0}/benchmarks/benchmark_distance_jax.py +0 -0
  103. {prosemble-2.2.0 → prosemble-2.4.0}/benchmarks/benchmark_fcm_jax.py +0 -0
  104. {prosemble-2.2.0 → prosemble-2.4.0}/benchmarks/benchmark_pcm_jax.py +0 -0
  105. {prosemble-2.2.0 → prosemble-2.4.0}/devenv.lock +0 -0
  106. {prosemble-2.2.0 → prosemble-2.4.0}/devenv.nix +0 -0
  107. {prosemble-2.2.0 → prosemble-2.4.0}/devenv.yaml +0 -0
  108. {prosemble-2.2.0 → prosemble-2.4.0}/examples/afcm_iris.py +0 -0
  109. {prosemble-2.2.0 → prosemble-2.4.0}/examples/bgpc_iris.py +0 -0
  110. {prosemble-2.2.0 → prosemble-2.4.0}/examples/cbc_iris.py +0 -0
  111. {prosemble-2.2.0 → prosemble-2.4.0}/examples/celvq_ng_iris.py +0 -0
  112. {prosemble-2.2.0 → prosemble-2.4.0}/examples/fcm_iris.py +0 -0
  113. {prosemble-2.2.0 → prosemble-2.4.0}/examples/fpcm_iris.py +0 -0
  114. {prosemble-2.2.0 → prosemble-2.4.0}/examples/glvq_advanced_iris.py +0 -0
  115. {prosemble-2.2.0 → prosemble-2.4.0}/examples/glvq_iris.py +0 -0
  116. {prosemble-2.2.0 → prosemble-2.4.0}/examples/glvq_unequal_prototypes_iris.py +0 -0
  117. {prosemble-2.2.0 → prosemble-2.4.0}/examples/gmlvq_iris.py +0 -0
  118. {prosemble-2.2.0 → prosemble-2.4.0}/examples/grlvq_iris.py +0 -0
  119. {prosemble-2.2.0 → prosemble-2.4.0}/examples/hcm_iris.py +0 -0
  120. {prosemble-2.2.0 → prosemble-2.4.0}/examples/heskes_som_iris.py +0 -0
  121. {prosemble-2.2.0 → prosemble-2.4.0}/examples/ipcm2_iris.py +0 -0
  122. {prosemble-2.2.0 → prosemble-2.4.0}/examples/ipcm_iris.py +0 -0
  123. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kafcm_iris.py +0 -0
  124. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kfcm_iris.py +0 -0
  125. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kfpcm_iris.py +0 -0
  126. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kipcm2_iris.py +0 -0
  127. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kipcm_iris.py +0 -0
  128. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kmeans_iris.py +0 -0
  129. {prosemble-2.2.0 → prosemble-2.4.0}/examples/knn_iris.py +0 -0
  130. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kohonen_som_iris.py +0 -0
  131. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kpcm_iris.py +0 -0
  132. {prosemble-2.2.0 → prosemble-2.4.0}/examples/kpfcm_iris.py +0 -0
  133. {prosemble-2.2.0 → prosemble-2.4.0}/examples/large_dataset_training.py +0 -0
  134. {prosemble-2.2.0 → prosemble-2.4.0}/examples/lcelvq_ng_iris.py +0 -0
  135. {prosemble-2.2.0 → prosemble-2.4.0}/examples/lmrslvq_iris.py +0 -0
  136. {prosemble-2.2.0 → prosemble-2.4.0}/examples/lmrslvq_ng_iris.py +0 -0
  137. {prosemble-2.2.0 → prosemble-2.4.0}/examples/lvq1_iris.py +0 -0
  138. {prosemble-2.2.0 → prosemble-2.4.0}/examples/lvqmln_iris.py +0 -0
  139. {prosemble-2.2.0 → prosemble-2.4.0}/examples/mcelvq_ng_iris.py +0 -0
  140. {prosemble-2.2.0 → prosemble-2.4.0}/examples/mrslvq_iris.py +0 -0
  141. {prosemble-2.2.0 → prosemble-2.4.0}/examples/mrslvq_ng_iris.py +0 -0
  142. {prosemble-2.2.0 → prosemble-2.4.0}/examples/neural_gas_iris.py +0 -0
  143. {prosemble-2.2.0 → prosemble-2.4.0}/examples/npc_iris.py +0 -0
  144. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_lmrslvq_iris.py +0 -0
  145. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_lmrslvq_ng_iris.py +0 -0
  146. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_mrslvq_iris.py +0 -0
  147. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_mrslvq_ng_iris.py +0 -0
  148. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_rslvq_iris.py +0 -0
  149. {prosemble-2.2.0 → prosemble-2.4.0}/examples/oc_rslvq_ng_iris.py +0 -0
  150. {prosemble-2.2.0 → prosemble-2.4.0}/examples/pcm_iris.py +0 -0
  151. {prosemble-2.2.0 → prosemble-2.4.0}/examples/pfcm_iris.py +0 -0
  152. {prosemble-2.2.0 → prosemble-2.4.0}/examples/plvq_iris.py +0 -0
  153. {prosemble-2.2.0 → prosemble-2.4.0}/examples/rslvq_ng_iris.py +0 -0
  154. {prosemble-2.2.0 → prosemble-2.4.0}/examples/slng_iris.py +0 -0
  155. {prosemble-2.2.0 → prosemble-2.4.0}/examples/smng_iris.py +0 -0
  156. {prosemble-2.2.0 → prosemble-2.4.0}/examples/som_iris.py +0 -0
  157. {prosemble-2.2.0 → prosemble-2.4.0}/examples/srng_iris.py +0 -0
  158. {prosemble-2.2.0 → prosemble-2.4.0}/examples/stng_iris.py +0 -0
  159. {prosemble-2.2.0 → prosemble-2.4.0}/examples/tcelvq_ng_iris.py +0 -0
  160. {prosemble-2.2.0 → prosemble-2.4.0}/examples/vis_fcm_iris.py +0 -0
  161. {prosemble-2.2.0 → prosemble-2.4.0}/examples/vis_glvq_iris.py +0 -0
  162. {prosemble-2.2.0 → prosemble-2.4.0}/examples/vis_neural_gas_iris.py +0 -0
  163. {prosemble-2.2.0 → prosemble-2.4.0}/examples/vis_som_iris.py +0 -0
  164. {prosemble-2.2.0 → prosemble-2.4.0}/flake.nix +0 -0
  165. {prosemble-2.2.0 → prosemble-2.4.0}/mkdocs.yml +0 -0
  166. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/__init__.py +0 -0
  167. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/activations.py +0 -0
  168. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/callbacks.py +0 -0
  169. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/competitions.py +0 -0
  170. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/data.py +0 -0
  171. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/distributed.py +0 -0
  172. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/initializers.py +0 -0
  173. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/kernel.py +0 -0
  174. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/losses.py +0 -0
  175. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/model_selection.py +0 -0
  176. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/pipeline.py +0 -0
  177. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/pooling.py +0 -0
  178. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/protocols.py +0 -0
  179. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/quantization.py +0 -0
  180. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/serialization.py +0 -0
  181. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/similarities.py +0 -0
  182. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/utils.py +0 -0
  183. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/vis.py +0 -0
  184. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/core/visualizer.py +0 -0
  185. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/datasets/__init__.py +0 -0
  186. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/datasets/dataset.py +0 -0
  187. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/afcm.py +0 -0
  188. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/base.py +0 -0
  189. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/bgpc.py +0 -0
  190. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/cbc.py +0 -0
  191. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/celvq_ng.py +0 -0
  192. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/crossentropy_lvq.py +0 -0
  193. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_heskes_som.py +0 -0
  194. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_kohonen_som.py +0 -0
  195. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/dk_neural_gas.py +0 -0
  196. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/fcm.py +0 -0
  197. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/fpcm.py +0 -0
  198. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/glvq.py +0 -0
  199. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/growing_neural_gas.py +0 -0
  200. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/hcm.py +0 -0
  201. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/heskes_som.py +0 -0
  202. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/image_cbc.py +0 -0
  203. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/image_lvq.py +0 -0
  204. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/ipcm.py +0 -0
  205. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/ipcm2.py +0 -0
  206. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kafcm.py +0 -0
  207. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kfcm.py +0 -0
  208. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kfpcm.py +0 -0
  209. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kipcm.py +0 -0
  210. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kipcm2.py +0 -0
  211. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kmeans.py +0 -0
  212. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/knn.py +0 -0
  213. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kohonen_som.py +0 -0
  214. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kpcm.py +0 -0
  215. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/kpfcm.py +0 -0
  216. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/lcelvq_ng.py +0 -0
  217. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/lvq1.py +0 -0
  218. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/lvq21.py +0 -0
  219. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/lvqmln.py +0 -0
  220. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/matrix_rslvq.py +0 -0
  221. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/mcelvq_ng.py +0 -0
  222. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/median_lvq.py +0 -0
  223. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/neural_gas.py +0 -0
  224. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/npc.py +0 -0
  225. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_glvq_ng.py +0 -0
  226. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_matrix_lvq_ng.py +0 -0
  227. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_dk_relevance_lvq_ng.py +0 -0
  228. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_glvq_ng.py +0 -0
  229. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_gmlvq_ng.py +0 -0
  230. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_grlvq_ng.py +0 -0
  231. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_gtlvq_ng.py +0 -0
  232. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_lgmlvq_ng.py +0 -0
  233. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_mrslvq_ng.py +0 -0
  234. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/oc_rslvq_ng.py +0 -0
  235. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/pcm.py +0 -0
  236. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/pfcm.py +0 -0
  237. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/plvq.py +0 -0
  238. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/probabilistic_lvq.py +0 -0
  239. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/siamese_lvq.py +0 -0
  240. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/som.py +0 -0
  241. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/svq_occ_lm.py +0 -0
  242. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/svq_occ_m.py +0 -0
  243. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/svq_occ_r.py +0 -0
  244. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/svq_occ_t.py +0 -0
  245. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/models/tcelvq_ng.py +0 -0
  246. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble/py.typed +0 -0
  247. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble.egg-info/dependency_links.txt +0 -0
  248. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble.egg-info/requires.txt +0 -0
  249. {prosemble-2.2.0 → prosemble-2.4.0}/prosemble.egg-info/top_level.txt +0 -0
  250. {prosemble-2.2.0 → prosemble-2.4.0}/requirements_docs.txt +0 -0
  251. {prosemble-2.2.0 → prosemble-2.4.0}/setup.cfg +0 -0
  252. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/Makefile +0 -0
  253. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/clustering.rst +0 -0
  254. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/one_class.rst +0 -0
  255. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/guides/topology.rst +0 -0
  256. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/index.rst +0 -0
  257. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/installation.rst +0 -0
  258. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/make.bat +0 -0
  259. {prosemble-2.2.0 → prosemble-2.4.0}/sphinx-docs/quickstart.rst +0 -0
  260. {prosemble-2.2.0 → prosemble-2.4.0}/tests/__init__.py +0 -0
  261. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_activations.py +0 -0
  262. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_cbc.py +0 -0
  263. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_celvq_ng.py +0 -0
  264. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_checkpoint.py +0 -0
  265. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_clustering_patience.py +0 -0
  266. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_competitions.py +0 -0
  267. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_core.py +0 -0
  268. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_core_jax.py +0 -0
  269. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_data.py +0 -0
  270. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_dataset.py +0 -0
  271. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_dataset_jax.py +0 -0
  272. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_distance_jax.py +0 -0
  273. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_distributed.py +0 -0
  274. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_dk_models.py +0 -0
  275. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_dk_ng_models.py +0 -0
  276. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_examples.sh +0 -0
  277. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_fcm_jax.py +0 -0
  278. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_glvq.py +0 -0
  279. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_gmlvq.py +0 -0
  280. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_heskes_som.py +0 -0
  281. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_image_lvq.py +0 -0
  282. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_initializers.py +0 -0
  283. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_jax_models.py +0 -0
  284. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_jit_inference.py +0 -0
  285. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_kohonen_som.py +0 -0
  286. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_lcelvq_ng.py +0 -0
  287. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_losses.py +0 -0
  288. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_lvq_nongradient.py +0 -0
  289. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_lvqmln_plvq.py +0 -0
  290. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_matrix_rslvq.py +0 -0
  291. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_mcelvq_ng.py +0 -0
  292. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_minibatch.py +0 -0
  293. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_mixed_precision.py +0 -0
  294. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_model_selection.py +0 -0
  295. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_mrslvq_ng.py +0 -0
  296. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_neural_gas.py +0 -0
  297. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_dk_models.py +0 -0
  298. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_dk_ng_models.py +0 -0
  299. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_glvq.py +0 -0
  300. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_glvq_ng.py +0 -0
  301. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_glvq_variants.py +0 -0
  302. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_mrslvq.py +0 -0
  303. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_rslvq.py +0 -0
  304. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_oc_rslvq_ng.py +0 -0
  305. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_pcm_jax.py +0 -0
  306. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_pfcm_jax.py +0 -0
  307. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_pipeline.py +0 -0
  308. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_pooling.py +0 -0
  309. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_probabilistic.py +0 -0
  310. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_protocols.py +0 -0
  311. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_prototype_base.py +0 -0
  312. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_quantization.py +0 -0
  313. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_riemannian_neural_gas.py +0 -0
  314. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_riemannian_supervised_ng.py +0 -0
  315. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_rslvq_ng.py +0 -0
  316. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_scan_training.py +0 -0
  317. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_serialization.py +0 -0
  318. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_siamese_lvq.py +0 -0
  319. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_similarities.py +0 -0
  320. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_slng.py +0 -0
  321. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_smng.py +0 -0
  322. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_srng.py +0 -0
  323. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_stng.py +0 -0
  324. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_svq_occ.py +0 -0
  325. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_svq_occ_r.py +0 -0
  326. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_svq_occ_variants.py +0 -0
  327. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_tcelvq_ng.py +0 -0
  328. {prosemble-2.2.0 → prosemble-2.4.0}/tests/test_vis.py +0 -0
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: prosemble
3
- Version: 2.2.0
3
+ Version: 2.4.0
4
4
  Summary: A python project for prototype-based machine learning models
5
5
  Author-email: Nana Abeka Otoo <nanaabekaotoo@gmail.com>
6
6
  License: MIT
@@ -5,8 +5,8 @@
5
5
  # 2. Add to pkgs/top-level/python-packages.nix:
6
6
  # prosemble = callPackage ../development/python-modules/prosemble { };
7
7
  # 3. Update the hash after publishing to PyPI:
8
- # nix-prefetch-url --unpack https://github.com/naotoo1/prosemble/archive/refs/tags/v2.0.0.tar.gz
9
- # 4. PR title: python3Packages.prosemble: init at 2.0.0
8
+ # nix-prefetch-url --unpack https://github.com/naotoo1/prosemble/archive/refs/tags/v2.3.0.tar.gz
9
+ # 4. PR title: python3Packages.prosemble: init at 2.3.0
10
10
  {
11
11
  lib,
12
12
  buildPythonPackage,
@@ -29,14 +29,14 @@
29
29
 
30
30
  buildPythonPackage (finalAttrs: {
31
31
  pname = "prosemble";
32
- version = "2.0.0";
32
+ version = "2.3.0";
33
33
  pyproject = true;
34
34
 
35
35
  src = fetchFromGitHub {
36
36
  owner = "naotoo1";
37
37
  repo = "prosemble";
38
- rev = "refs/tags/v${finalAttrs.version}";
39
- hash = "sha256-6Oa7V7tFle74oYBNEaJ1ZCrrku8cav92YkzpnCxsH5c=";
38
+ tag = "v${finalAttrs.version}";
39
+ hash = "sha256-296Z1lHBcOVQbkfO7KlNnWe7f7xjbKFHJRfGUPaHKWY=";
40
40
  };
41
41
 
42
42
  build-system = [
@@ -68,6 +68,7 @@ buildPythonPackage (finalAttrs: {
68
68
  ];
69
69
 
70
70
  disabledTestPaths = [
71
+ # Requires geomstats which is not packaged
71
72
  "tests/test_riemannian_neural_gas.py"
72
73
  ];
73
74
 
@@ -77,11 +78,11 @@ buildPythonPackage (finalAttrs: {
77
78
  "prosemble.core"
78
79
  ];
79
80
 
80
- meta = with lib; {
81
+ meta = {
81
82
  description = "JAX-based prototype machine learning library";
82
83
  homepage = "https://github.com/naotoo1/prosemble";
83
84
  changelog = "https://github.com/naotoo1/prosemble/releases/tag/v${finalAttrs.version}";
84
- license = licenses.mit;
85
- maintainers = with maintainers; [ ];
85
+ license = lib.licenses.mit;
86
+ maintainers = with lib.maintainers; [ naotoo1 ];
86
87
  };
87
88
  })
@@ -41,6 +41,19 @@ from .protocols import (
41
41
  from .serialization import SerializationMixin
42
42
  from .data import shuffle_arrays, padded_batches, batched_iterator
43
43
  from .distributed import create_mesh, shard_data, replicate_params
44
+ from .optimizers import per_group_clip, hypergradient_descent, riemannian_nesterov
45
+ from .regularization import (
46
+ prototype_diversity_loss, prototype_diversity_loss_vectorized,
47
+ sparse_relevance_proximal, elastic_net_proximal,
48
+ )
49
+ from .curriculum import (
50
+ curriculum_weights, curriculum_threshold, apply_curriculum_to_loss,
51
+ )
52
+ from .reject import RejectOptionMixin
53
+ from .geodesic import (
54
+ geodesic_interpolation, geodesic_midpoint, decision_boundary_point,
55
+ prototype_geodesic_distances, inter_class_geodesics,
56
+ )
44
57
 
45
58
  try:
46
59
  import jax
@@ -93,6 +106,18 @@ __all__ = _distance_all + [
93
106
  'shuffle_arrays', 'padded_batches', 'batched_iterator',
94
107
  # Distributed training
95
108
  'create_mesh', 'shard_data', 'replicate_params',
109
+ # Custom optimizers
110
+ 'per_group_clip', 'hypergradient_descent', 'riemannian_nesterov',
111
+ # Regularization
112
+ 'prototype_diversity_loss', 'prototype_diversity_loss_vectorized',
113
+ 'sparse_relevance_proximal', 'elastic_net_proximal',
114
+ # Curriculum learning
115
+ 'curriculum_weights', 'curriculum_threshold', 'apply_curriculum_to_loss',
116
+ # Reject option
117
+ 'RejectOptionMixin',
118
+ # Geodesic interpolation
119
+ 'geodesic_interpolation', 'geodesic_midpoint', 'decision_boundary_point',
120
+ 'prototype_geodesic_distances', 'inter_class_geodesics',
96
121
  # ONNX export (optional)
97
122
  'export_onnx',
98
123
  ]
@@ -0,0 +1,171 @@
1
+ """Curriculum learning (self-paced learning) for prototype-based models.
2
+
3
+ Implements the self-paced learning framework (Kumar et al. 2010) adapted
4
+ for LVQ models. Samples are presented in order of difficulty — easy
5
+ samples first, hard samples later.
6
+
7
+ For LVQ, sample difficulty is measured by the absolute value of the
8
+ mu-ratio: |mu(x)| close to 0 means the sample is on the decision
9
+ boundary (hard), while |mu(x)| >> 0 means it's far from the boundary
10
+ (easy).
11
+
12
+ Usage
13
+ -----
14
+ Curriculum learning is applied via sample masking in the loss function.
15
+ At each training step, a difficulty threshold lambda_t determines which
16
+ samples participate. The threshold increases over training to gradually
17
+ include harder samples.
18
+
19
+ References
20
+ ----------
21
+ .. [1] Kumar, M. P., Packer, B., & Koller, D. (2010). Self-paced
22
+ learning for latent variable models. NeurIPS.
23
+ .. [2] Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009).
24
+ Curriculum learning. ICML.
25
+ """
26
+
27
+ import jax.numpy as jnp
28
+
29
+
30
+ def curriculum_weights(per_sample_loss, threshold, mode='hard'):
31
+ """Compute per-sample curriculum weights based on loss magnitude.
32
+
33
+ Parameters
34
+ ----------
35
+ per_sample_loss : array of shape (n_samples,)
36
+ Per-sample loss values (e.g., from GLVQ mu-ratio).
37
+ threshold : float
38
+ Difficulty threshold lambda_t. Samples with loss below this
39
+ threshold are included. Increases over training.
40
+ mode : str, {'hard', 'soft', 'linear'}
41
+ Weight assignment mode:
42
+ - 'hard': binary weights (0 or 1). Sample is either in or out.
43
+ - 'soft': smooth exponential weighting.
44
+ w_i = exp(-loss_i / threshold) if loss_i > threshold, else 1.
45
+ - 'linear': linear ramp-down.
46
+ w_i = max(0, 1 - (loss_i - threshold) / threshold).
47
+ Default: 'hard'.
48
+
49
+ Returns
50
+ -------
51
+ weights : array of shape (n_samples,)
52
+ Per-sample weights in [0, 1]. Weights sum is used to normalize
53
+ the loss.
54
+ """
55
+ if mode == 'hard':
56
+ return jnp.where(per_sample_loss <= threshold, 1.0, 0.0)
57
+ elif mode == 'soft':
58
+ # Smooth transition: full weight below threshold, exponential decay above
59
+ excess = jnp.maximum(per_sample_loss - threshold, 0.0)
60
+ return jnp.exp(-excess / (threshold + 1e-10))
61
+ elif mode == 'linear':
62
+ # Linear ramp-down above threshold
63
+ return jnp.clip(1.0 - (per_sample_loss - threshold) / (threshold + 1e-10), 0.0, 1.0)
64
+ else:
65
+ raise ValueError(f"Unknown curriculum mode '{mode}'. Use 'hard', 'soft', or 'linear'.")
66
+
67
+
68
+ def curriculum_threshold(iteration, max_iter, init_threshold=0.3,
69
+ final_threshold=None, schedule='linear'):
70
+ """Compute the difficulty threshold at a given training iteration.
71
+
72
+ The threshold increases over training: initially only easy samples
73
+ are included, and harder samples are gradually added.
74
+
75
+ Parameters
76
+ ----------
77
+ iteration : int or array
78
+ Current training iteration.
79
+ max_iter : int
80
+ Maximum number of iterations.
81
+ init_threshold : float
82
+ Initial threshold (fraction of max loss to include). At the
83
+ start, only samples with loss < init_threshold * max_loss are
84
+ included. Default: 0.3.
85
+ final_threshold : float, optional
86
+ Final threshold. Default: None (uses a large value to include
87
+ all samples by end of training).
88
+ schedule : str, {'linear', 'exponential', 'cosine'}
89
+ How the threshold grows over training:
90
+ - 'linear': lambda_t = init + (final - init) * t / T
91
+ - 'exponential': lambda_t = init * (final / init) ^ (t / T)
92
+ - 'cosine': cosine annealing from init to final.
93
+ Default: 'linear'.
94
+
95
+ Returns
96
+ -------
97
+ threshold : float
98
+ Difficulty threshold at the current iteration.
99
+ """
100
+ if final_threshold is None:
101
+ final_threshold = 100.0 # Effectively include all samples
102
+
103
+ progress = jnp.clip(iteration / jnp.maximum(max_iter - 1, 1), 0.0, 1.0)
104
+
105
+ if schedule == 'linear':
106
+ return init_threshold + (final_threshold - init_threshold) * progress
107
+ elif schedule == 'exponential':
108
+ # Avoid log(0): ensure init > 0
109
+ log_ratio = jnp.log(final_threshold / (init_threshold + 1e-10))
110
+ return init_threshold * jnp.exp(log_ratio * progress)
111
+ elif schedule == 'cosine':
112
+ # Cosine annealing: starts slow, accelerates, then slows
113
+ cosine_factor = 0.5 * (1.0 - jnp.cos(jnp.pi * progress))
114
+ return init_threshold + (final_threshold - init_threshold) * cosine_factor
115
+ else:
116
+ raise ValueError(
117
+ f"Unknown schedule '{schedule}'. Use 'linear', 'exponential', or 'cosine'."
118
+ )
119
+
120
+
121
+ def apply_curriculum_to_loss(per_sample_losses, iteration, max_iter,
122
+ init_percentile=0.3, schedule='linear',
123
+ mode='soft'):
124
+ """Full curriculum pipeline: compute threshold and weighted loss.
125
+
126
+ Convenience function that combines threshold scheduling and weight
127
+ computation. Use inside ``_compute_loss`` to add curriculum learning
128
+ to any model.
129
+
130
+ Parameters
131
+ ----------
132
+ per_sample_losses : array of shape (n_samples,)
133
+ Per-sample loss values.
134
+ iteration : int or array
135
+ Current training step.
136
+ max_iter : int
137
+ Total training steps.
138
+ init_percentile : float
139
+ Initial fraction of samples to include (by loss quantile).
140
+ Default: 0.3 (include the easiest 30% of samples initially).
141
+ schedule : str
142
+ Threshold growth schedule. Default: 'linear'.
143
+ mode : str
144
+ Weighting mode. Default: 'soft'.
145
+
146
+ Returns
147
+ -------
148
+ weighted_loss : scalar
149
+ Curriculum-weighted mean loss.
150
+ """
151
+ # Estimate threshold from loss statistics
152
+ # Use quantile of current losses as adaptive threshold
153
+ sorted_losses = jnp.sort(per_sample_losses)
154
+ n = per_sample_losses.shape[0]
155
+
156
+ # Progress determines what fraction of samples to include
157
+ progress = jnp.clip(iteration / jnp.maximum(max_iter - 1, 1), 0.0, 1.0)
158
+ # Start with init_percentile fraction, end with all samples
159
+ include_frac = init_percentile + (1.0 - init_percentile) * progress
160
+
161
+ # Convert fraction to threshold via quantile
162
+ idx = jnp.clip((include_frac * n).astype(jnp.int32), 0, n - 1)
163
+ threshold = sorted_losses[idx]
164
+
165
+ weights = curriculum_weights(per_sample_losses, threshold, mode=mode)
166
+
167
+ # Weighted mean loss (avoid division by zero)
168
+ total_weight = jnp.sum(weights)
169
+ weighted_loss = jnp.sum(weights * per_sample_losses) / (total_weight + 1e-10)
170
+
171
+ return weighted_loss
@@ -431,6 +431,185 @@ def tangent_distance_matrix(
431
431
  return jnp.sum(tangent_diff ** 2, axis=2)
432
432
 
433
433
 
434
+ # ============================================================================
435
+ # Wasserstein Distance Functions
436
+ # ============================================================================
437
+
438
+
439
+ @jit
440
+ def wasserstein2_distance_matrix(
441
+ X: chex.Array,
442
+ means: chex.Array,
443
+ log_variances: chex.Array
444
+ ) -> chex.Array:
445
+ """
446
+ Compute pairwise squared 2-Wasserstein distances from points to Gaussian prototypes.
447
+
448
+ Each prototype is a diagonal Gaussian :math:`\\mathcal{N}(\\mu_k, \\text{diag}(\\sigma_k^2))`.
449
+ Each input point :math:`x` is treated as a Dirac delta distribution :math:`\\delta_x`.
450
+
451
+ The squared 2-Wasserstein distance from a point to a diagonal Gaussian is:
452
+
453
+ .. math::
454
+
455
+ W_2^2(\\delta_x, \\mathcal{N}(\\mu_k, \\text{diag}(\\sigma_k^2)))
456
+ = \\sum_j (x_j - \\mu_{kj})^2 + \\sum_j \\sigma_{kj}^2
457
+
458
+ This decomposes into the squared Euclidean distance from the point to the
459
+ mean, plus the total variance (trace of covariance). Prototypes with
460
+ smaller variance are effectively "more certain" and attract nearby points
461
+ more strongly.
462
+
463
+ Parameters
464
+ ----------
465
+ X : array of shape (n, d)
466
+ Data points.
467
+ means : array of shape (p, d)
468
+ Prototype mean vectors.
469
+ log_variances : array of shape (p, d)
470
+ Log of prototype variances (ensures positivity via ``exp``).
471
+
472
+ Returns
473
+ -------
474
+ D : array of shape (n, p)
475
+ Squared 2-Wasserstein distances.
476
+
477
+ References
478
+ ----------
479
+ .. [1] Villani, C. (2009). Optimal Transport: Old and New.
480
+ Springer. Chapter 2.
481
+ .. [2] Givens, C. R. & Shortt, R. M. (1984). A class of Wasserstein
482
+ metrics for probability distributions. Michigan Math. J., 31(2).
483
+ """
484
+ chex.assert_rank(X, 2)
485
+ chex.assert_rank(means, 2)
486
+ chex.assert_rank(log_variances, 2)
487
+ chex.assert_equal(X.shape[1], means.shape[1])
488
+ chex.assert_equal(means.shape, log_variances.shape)
489
+
490
+ # Squared Euclidean from points to means
491
+ eucl = squared_euclidean_distance_matrix(X, means) # (n, p)
492
+
493
+ # Variance spread penalty per prototype
494
+ variances = jnp.exp(log_variances) # (p, d)
495
+ spread = jnp.sum(variances, axis=1) # (p,)
496
+
497
+ return eucl + spread[None, :]
498
+
499
+
500
+ @jit
501
+ def wasserstein2_omega_distance_matrix(
502
+ X: chex.Array,
503
+ means: chex.Array,
504
+ log_variances: chex.Array,
505
+ omega: chex.Array
506
+ ) -> chex.Array:
507
+ """
508
+ Squared 2-Wasserstein distance with global metric adaptation.
509
+
510
+ Projects data and means through :math:`\\Omega` before computing
511
+ the Euclidean component, while variances contribute directly:
512
+
513
+ .. math::
514
+
515
+ W_2^2(x, k) = \\|\\Omega(x - \\mu_k)\\|^2 + \\sum_j \\sigma_{kj}^2
516
+
517
+ Parameters
518
+ ----------
519
+ X : array of shape (n, d)
520
+ Data points.
521
+ means : array of shape (p, d)
522
+ Prototype mean vectors.
523
+ log_variances : array of shape (p, d)
524
+ Log of prototype variances.
525
+ omega : array of shape (d, l)
526
+ Global projection matrix.
527
+
528
+ Returns
529
+ -------
530
+ D : array of shape (n, p)
531
+ Squared 2-Wasserstein distances in projected space.
532
+ """
533
+ chex.assert_rank(X, 2)
534
+ chex.assert_rank(means, 2)
535
+ chex.assert_rank(log_variances, 2)
536
+ chex.assert_rank(omega, 2)
537
+ chex.assert_equal(X.shape[1], means.shape[1])
538
+ chex.assert_equal(means.shape, log_variances.shape)
539
+ chex.assert_equal(X.shape[1], omega.shape[0])
540
+
541
+ # Project and compute squared Euclidean in projected space
542
+ X_proj = X @ omega # (n, l)
543
+ M_proj = means @ omega # (p, l)
544
+ eucl = squared_euclidean_distance_matrix(X_proj, M_proj) # (n, p)
545
+
546
+ # Variance spread penalty
547
+ variances = jnp.exp(log_variances) # (p, d)
548
+ spread = jnp.sum(variances, axis=1) # (p,)
549
+
550
+ return eucl + spread[None, :]
551
+
552
+
553
+ @jit
554
+ def wasserstein2_relevance_distance_matrix(
555
+ X: chex.Array,
556
+ means: chex.Array,
557
+ log_variances: chex.Array,
558
+ relevances: chex.Array
559
+ ) -> chex.Array:
560
+ """
561
+ Squared 2-Wasserstein distance with feature relevance weighting.
562
+
563
+ Applies per-feature relevance weights :math:`\\lambda_j` to the
564
+ Euclidean component:
565
+
566
+ .. math::
567
+
568
+ W_2^2(x, k) = \\sum_j \\lambda_j (x_j - \\mu_{kj})^2 + \\sum_j \\sigma_{kj}^2
569
+
570
+ where :math:`\\lambda_j = \\text{softmax}(r)_j` ensures non-negative
571
+ weights that sum to 1.
572
+
573
+ Parameters
574
+ ----------
575
+ X : array of shape (n, d)
576
+ Data points.
577
+ means : array of shape (p, d)
578
+ Prototype mean vectors.
579
+ log_variances : array of shape (p, d)
580
+ Log of prototype variances.
581
+ relevances : array of shape (d,)
582
+ Raw relevance logits (softmax applied internally).
583
+
584
+ Returns
585
+ -------
586
+ D : array of shape (n, p)
587
+ Relevance-weighted squared 2-Wasserstein distances.
588
+ """
589
+ chex.assert_rank(X, 2)
590
+ chex.assert_rank(means, 2)
591
+ chex.assert_rank(log_variances, 2)
592
+ chex.assert_rank(relevances, 1)
593
+ chex.assert_equal(X.shape[1], means.shape[1])
594
+ chex.assert_equal(means.shape, log_variances.shape)
595
+ chex.assert_equal(X.shape[1], relevances.shape[0])
596
+
597
+ # Softmax relevance weights
598
+ lambdas = jax.nn.softmax(relevances) # (d,)
599
+
600
+ # Weighted squared differences
601
+ # (n, 1, d) - (1, p, d) -> (n, p, d)
602
+ diff_sq = (X[:, None, :] - means[None, :, :]) ** 2
603
+ weighted = diff_sq * lambdas[None, None, :] # (n, p, d)
604
+ eucl = jnp.sum(weighted, axis=2) # (n, p)
605
+
606
+ # Variance spread penalty
607
+ variances = jnp.exp(log_variances) # (p, d)
608
+ spread = jnp.sum(variances, axis=1) # (p,)
609
+
610
+ return eucl + spread[None, :]
611
+
612
+
434
613
  # ============================================================================
435
614
  # Kernel Functions
436
615
  # ============================================================================
@@ -764,6 +943,10 @@ __all__ = [
764
943
  'omega_distance_matrix',
765
944
  'lomega_distance_matrix',
766
945
  'tangent_distance_matrix',
946
+ # Wasserstein distance functions
947
+ 'wasserstein2_distance_matrix',
948
+ 'wasserstein2_omega_distance_matrix',
949
+ 'wasserstein2_relevance_distance_matrix',
767
950
  # Kernel functions
768
951
  'gaussian_kernel_matrix',
769
952
  'polynomial_kernel_matrix',
@@ -0,0 +1,217 @@
1
+ """Geodesic interpolation and boundary visualization for Riemannian models.
2
+
3
+ Computes geodesic paths between prototypes on Riemannian manifolds for
4
+ decision boundary visualization and model interpretation.
5
+
6
+ On curved manifolds, the decision boundary (locus where d(x, w_i) = d(x, w_j))
7
+ is not a hyperplane — it's a curved surface. Geodesic interpolation allows
8
+ us to:
9
+ 1. Visualize the path between prototypes along the manifold.
10
+ 2. Find the approximate decision boundary point along geodesics.
11
+ 3. Compute prototype midpoints respecting manifold geometry.
12
+
13
+ References
14
+ ----------
15
+ .. [1] Absil, P.-A., Mahony, R., & Sepulchre, R. (2008). Optimization
16
+ Algorithms on Matrix Manifolds. Princeton University Press.
17
+ """
18
+
19
+ import jax.numpy as jnp
20
+
21
+
22
+ def geodesic_interpolation(manifold, point_a, point_b, n_points=50):
23
+ """Compute a geodesic path between two points on a manifold.
24
+
25
+ Uses the exponential map to trace the shortest path (geodesic)
26
+ between two manifold points:
27
+
28
+ .. math::
29
+
30
+ \\gamma(t) = \\text{Exp}_{w_a}(t \\cdot \\text{Log}_{w_a}(w_b)),
31
+ \\quad t \\in [0, 1]
32
+
33
+ Parameters
34
+ ----------
35
+ manifold : SO, SPD, or Grassmannian
36
+ Riemannian manifold instance with ``exp_map`` and ``log_map``.
37
+ point_a : array
38
+ Starting point on the manifold.
39
+ point_b : array
40
+ End point on the manifold.
41
+ n_points : int
42
+ Number of interpolation points along the geodesic.
43
+ Default: 50.
44
+
45
+ Returns
46
+ -------
47
+ path : array of shape (n_points, ...)
48
+ Points along the geodesic from point_a to point_b.
49
+ Each point lies on the manifold.
50
+ """
51
+ # Compute the tangent vector from a to b
52
+ tangent = manifold.log_map(point_a, point_b)
53
+
54
+ # Interpolate along the geodesic
55
+ t_values = jnp.linspace(0.0, 1.0, n_points)
56
+ path = []
57
+ for t in t_values:
58
+ point = manifold.exp_map(point_a, t * tangent)
59
+ path.append(point)
60
+
61
+ return jnp.stack(path, axis=0)
62
+
63
+
64
+ def geodesic_midpoint(manifold, point_a, point_b):
65
+ """Compute the geodesic midpoint between two manifold points.
66
+
67
+ The midpoint is at t = 0.5 along the geodesic:
68
+
69
+ .. math::
70
+
71
+ m = \\text{Exp}_{w_a}(0.5 \\cdot \\text{Log}_{w_a}(w_b))
72
+
73
+ Parameters
74
+ ----------
75
+ manifold : SO, SPD, or Grassmannian
76
+ Riemannian manifold instance.
77
+ point_a : array
78
+ First manifold point.
79
+ point_b : array
80
+ Second manifold point.
81
+
82
+ Returns
83
+ -------
84
+ midpoint : array
85
+ Geodesic midpoint, guaranteed to lie on the manifold.
86
+ """
87
+ tangent = manifold.log_map(point_a, point_b)
88
+ return manifold.exp_map(point_a, 0.5 * tangent)
89
+
90
+
91
+ def decision_boundary_point(manifold, proto_a, proto_b, n_search=100):
92
+ """Find the decision boundary point along the geodesic between prototypes.
93
+
94
+ On curved manifolds, the equidistant point (where d(x, w_a) = d(x, w_b))
95
+ is not necessarily at t = 0.5. This function searches along the geodesic
96
+ for the point where distances to both prototypes are equal.
97
+
98
+ Parameters
99
+ ----------
100
+ manifold : SO, SPD, or Grassmannian
101
+ Riemannian manifold instance.
102
+ proto_a : array
103
+ First prototype (on manifold).
104
+ proto_b : array
105
+ Second prototype (on manifold).
106
+ n_search : int
107
+ Number of candidate points to evaluate. Default: 100.
108
+
109
+ Returns
110
+ -------
111
+ boundary_point : array
112
+ Point on the geodesic where d(point, proto_a) = d(point, proto_b).
113
+ t_boundary : float
114
+ Parameter value t in [0, 1] where the boundary lies.
115
+ t = 0.5 for symmetric manifolds, may differ on curved spaces.
116
+ """
117
+ tangent = manifold.log_map(proto_a, proto_b)
118
+ t_values = jnp.linspace(0.0, 1.0, n_search)
119
+
120
+ # Compute distance difference at each point along the geodesic
121
+ def distance_diff(t):
122
+ point = manifold.exp_map(proto_a, t * tangent)
123
+ d_a = manifold.distance(point, proto_a)
124
+ d_b = manifold.distance(point, proto_b)
125
+ return jnp.abs(d_a - d_b)
126
+
127
+ diffs = jnp.array([distance_diff(t) for t in t_values])
128
+ best_idx = jnp.argmin(diffs)
129
+ t_boundary = t_values[best_idx]
130
+ boundary_point = manifold.exp_map(proto_a, t_boundary * tangent)
131
+
132
+ return boundary_point, float(t_boundary)
133
+
134
+
135
+ def prototype_geodesic_distances(manifold, prototypes, proto_labels):
136
+ """Compute pairwise geodesic distances between prototypes.
137
+
138
+ Parameters
139
+ ----------
140
+ manifold : SO, SPD, or Grassmannian
141
+ Riemannian manifold instance.
142
+ prototypes : array of shape (n_prototypes, ...)
143
+ Prototype points on the manifold (flattened).
144
+ proto_labels : array of shape (n_prototypes,)
145
+ Class labels for prototypes.
146
+
147
+ Returns
148
+ -------
149
+ distances : array of shape (n_prototypes, n_prototypes)
150
+ Pairwise geodesic distance matrix.
151
+ """
152
+ n = prototypes.shape[0]
153
+ distances = jnp.zeros((n, n))
154
+
155
+ for i in range(n):
156
+ for j in range(i + 1, n):
157
+ d = manifold.distance(prototypes[i], prototypes[j])
158
+ distances = distances.at[i, j].set(d)
159
+ distances = distances.at[j, i].set(d)
160
+
161
+ return distances
162
+
163
+
164
+ def inter_class_geodesics(manifold, prototypes, proto_labels, n_points=50):
165
+ """Compute geodesic paths between all inter-class prototype pairs.
166
+
167
+ Useful for visualizing decision boundaries: the boundary between
168
+ two classes lies somewhere along the geodesic connecting their
169
+ closest prototypes.
170
+
171
+ Parameters
172
+ ----------
173
+ manifold : SO, SPD, or Grassmannian
174
+ Riemannian manifold instance.
175
+ prototypes : array of shape (n_prototypes, ...)
176
+ Prototype positions on manifold.
177
+ proto_labels : array of shape (n_prototypes,)
178
+ Class labels.
179
+ n_points : int
180
+ Points per geodesic path. Default: 50.
181
+
182
+ Returns
183
+ -------
184
+ geodesics : list of dict
185
+ Each dict contains:
186
+ - 'path': array of shape (n_points, ...) — geodesic path
187
+ - 'proto_a_idx': int — index of first prototype
188
+ - 'proto_b_idx': int — index of second prototype
189
+ - 'class_a': int — class of first prototype
190
+ - 'class_b': int — class of second prototype
191
+ - 'boundary_t': float — approximate boundary location
192
+ """
193
+ import numpy as np
194
+
195
+ n = prototypes.shape[0]
196
+ labels_np = np.asarray(proto_labels)
197
+ geodesics = []
198
+
199
+ for i in range(n):
200
+ for j in range(i + 1, n):
201
+ if labels_np[i] != labels_np[j]:
202
+ path = geodesic_interpolation(
203
+ manifold, prototypes[i], prototypes[j], n_points
204
+ )
205
+ _, t_boundary = decision_boundary_point(
206
+ manifold, prototypes[i], prototypes[j]
207
+ )
208
+ geodesics.append({
209
+ 'path': path,
210
+ 'proto_a_idx': i,
211
+ 'proto_b_idx': j,
212
+ 'class_a': int(labels_np[i]),
213
+ 'class_b': int(labels_np[j]),
214
+ 'boundary_t': t_boundary,
215
+ })
216
+
217
+ return geodesics