qpytorch 0.1__py3-none-any.whl → 0.1.1__py3-none-any.whl

qpytorch/version.py

@@ -1,4 +1,4 @@
 # file generated by setuptools_scm
 # don't change, don't track in version control
-__version__ = version = '0.1'
-__version_tuple__ = version_tuple = (0, 1)
+__version__ = version = '0.1.1'
+__version_tuple__ = version_tuple = (0, 1, 1)

{qpytorch-0.1.dist-info → qpytorch-0.1.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qpytorch
-Version: 0.1
+Version: 0.1.1
 Summary: An implementation of Q-Exponential Processes in Pytorch based on GPyTorch
 Home-page: https://lanzithinking.github.io/qepytorch/
 Author: Shiwei Lan
@@ -19,6 +19,7 @@ Requires-Dist: scikit-learn
 Requires-Dist: scipy>=1.6.0
 Requires-Dist: linear-operator>=0.6
 Requires-Dist: gpytorch>=1.13
+Requires-Dist: numpy<2
 Provides-Extra: dev
 Requires-Dist: pre-commit; extra == "dev"
 Requires-Dist: setuptools-scm; extra == "dev"
@@ -63,60 +64,61 @@ Requires-Dist: nbval; extra == "test"
 [![License](https://img.shields.io/badge/license-MIT-green.svg)](LICENSE)
 
 [![Python Version](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
-[![Conda](https://img.shields.io/conda/v/conda-forge/qpytorch.svg)](https://anaconda.org/conda-forge/qpytorch)
+[![Conda](https://img.shields.io/conda/v/qpytorch.svg)](https://anaconda.org/qpytorch)
 [![PyPI](https://img.shields.io/pypi/v/qpytorch.svg)](https://pypi.org/project/qpytorch)
 
-Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is a Q-exponential process library implemented using PyTorch built on [GPyTorch](https://gpytorch.ai). Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is designed for creating scalable, flexible, and modular Q-exponential process models with ease.
+Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is a Python package for Q-exponential process ([QEP](https://papers.nips.cc/paper_files/paper/2023/file/e6bfdd58f1326ff821a1b92743963bdf-Paper-Conference.pdf)) implemented using PyTorch and built up on [GPyTorch](https://gpytorch.ai). Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is designed to facilitate creating scalable, flexible, and modular QPE models.
 
-Internally, Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch differs from many existing approaches to QEP inference by performing most inference operations using numerical linear algebra techniques like preconditioned conjugate gradients.
-Implementing a scalable QEP method is as simple as providing a matrix multiplication routine with the kernel matrix and its derivative via our [LinearOperator](https://github.com/cornellius-gp/linear_operator) interface,
-or by composing many of our already existing `LinearOperators`.
-This allows not only for easy implementation of popular scalable QEP techniques,
-but often also for significantly improved utilization of GPU computing compared to solvers based on the Cholesky decomposition.
+Different from GPyTorch for Gaussian process (GP) models, Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch focuses on QEP, which generalizes GP by allowing flexible regularization on function spaces through a parameter $q>0$ and embraces GP as a special case with $q=2$. QEP is proven to be superior than GP in modeling inhomogeneous objects with abrupt changes or sharp contrast for $q<2$ [[Li et al (2023)]](https://papers.nips.cc/paper_files/paper/2023/hash/e6bfdd58f1326ff821a1b92743963bdf-Abstract-Conference.html).
+Inherited from GPyTorch, Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch has an efficient and scalable implementation by taking advantage of numerical linear algebra library [LinearOperator](https://github.com/cornellius-gp/linear_operator) and improved GPU utilization.
 
-Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch provides (1) significant GPU acceleration (through MVM based inference);
-(2) state-of-the-art implementations of the latest algorithmic advances for scalability and flexibility ([SKI/KISS-GP](http://proceedings.mlr.press/v37/wilson15.pdf), [stochastic Lanczos expansions](https://arxiv.org/abs/1711.03481), [LOVE](https://arxiv.org/pdf/1803.06058.pdf), [SKIP](https://arxiv.org/pdf/1802.08903.pdf), [stochastic variational](https://arxiv.org/pdf/1611.00336.pdf) [deep kernel learning](http://proceedings.mlr.press/v51/wilson16.pdf), ...);
-(3) easy integration with deep learning frameworks.
 
+<!--
+Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch features ...
+-->
 
-## Examples, Tutorials, and Documentation
 
-See our [**documentation, examples, tutorials**](https://qepytorch.readthedocs.io/en/stable/) on how to construct all sorts of models in Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch.
+## Tutorials, Examples, and Documentation
+
+See [**documentation**](https://qepytorch.readthedocs.io/en/stable/) on how to construct various QEP models in Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch.
 
 ## Installation
 
 **Requirements**:
 - Python >= 3.10
-- PyTorch >= 2.2
+- PyTorch >= 2.0
 - GPyTorch >= 1.13
 
+#### Stable Version
+
 Install Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch using pip or conda:
 
 ```bash
 pip install qpytorch
-conda install qpytorch -c qpytorch
+conda install qpytorch
 ```
 
 (To use packages globally but install Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch as a user-only package, use `pip install --user` above.)
 
-#### Latest (Unstable) Version
+#### Latest Version
 
-To upgrade to the latest (unstable) version, run
+To upgrade to the latest version, run
 
 ```bash
-pip install --upgrade git+https://github.com/cornellius-gp/linear_operator.git
-pip install --upgrade git+https://github.com/cornellius-gp/gpytorch.git
 pip install --upgrade git+https://github.com/lanzithinking/qepytorch.git
 ```
 
-#### Development version
+#### from source (for development)
 
 If you are contributing a pull request, it is best to perform a manual installation:
 
 ```sh
-git clone https://github.com/lanzithinking/qepytorch.git qpytorch
-cd qpytorch
+git clone https://github.com/lanzithinking/qepytorch.git
+cd qepytorch
+# either
 pip install -e .[dev,docs,examples,keops,pyro,test]  # keops and pyro are optional
+# or
+conda env create -f env_install.yaml # installed in the environment qpytorch
 ```
 
 <!--
@@ -137,7 +139,7 @@ To discuss any issues related to this AUR package refer to the comments section
 
 ## Citing Us
 
-If you use Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch, please cite the following papers:
+If you use Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch, please cite the following paper:
 > [Li, Shuyi, Michael O'Connor, and Shiwei Lan. "Bayesian Learning via Q-Exponential Process." In Advances in Neural Information Processing Systems (2023).](https://papers.nips.cc/paper_files/paper/2023/hash/e6bfdd58f1326ff821a1b92743963bdf-Abstract-Conference.html)
 ```
 @inproceedings{li2023QEP,
@@ -159,18 +161,18 @@ for information on submitting issues and pull requests.
 Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is primarily maintained by:
 - [Shiwei Lan](https://math.la.asu.edu/~slan) (Arizona State University)
 
-We would like to thank our other contributors including (but not limited to)
-Shuyi Li,
+Thanks to the following contributors including (but not limited to)
+- Shuyi Li,
 Guangting Yu,
 Zhi Chang,
 Chukwudi Paul Obite,
 Keyan Wu,
 and many more!
 
-
+<!--
 ## Acknowledgements
 Development of Q<sup style="font-size: 0.5em;">&#9428;</sup>PyTorch is supported by.
-
+-->
 
 ## License
 

{qpytorch-0.1.dist-info → qpytorch-0.1.1.dist-info}/RECORD

@@ -1,6 +1,6 @@
 qpytorch/__init__.py,sha256=0sD7DfLvEXx3PvqrTyl5bOYprus1Wjzxs1hOzTbQx6s,12392
 qpytorch/module.py,sha256=xjw6X-v3_iVt4cOUEQdQp-cbTKkLCqwaeJoUardRQSQ,1259
-qpytorch/version.py,sha256=Ljuux5HvS-yDzAhpzt_WxHJ6Ct4dLQiCUJg2yT5NuzE,155
+qpytorch/version.py,sha256=aDfNBQh0vsVL7CSgYEMdMUbrxVw92raLxMivH20w2A4,160
 qpytorch/constraints/__init__.py,sha256=JS4bzSGrgAiDtOM_Y4rerzkoMAUt671E2U1SVakhfX4,138
 qpytorch/distributions/__init__.py,sha256=OSVX5Lfb72NKVFWVku0t-D2RyZuVcJAIICndOX9f5EA,973
 qpytorch/distributions/delta.py,sha256=AC-N5fhBQad872jl8q9PMLq46E5qwcQOXkRf1PSW-Cg,3507
@@ -95,8 +95,8 @@ qpytorch/variational/tril_natural_variational_distribution.py,sha256=3wPggMUY293
 qpytorch/variational/uncorrelated_multitask_variational_strategy.py,sha256=LdiVacUdQZ-BJDGcdHwlZ_uIVPfRl1WAgEtfs3ahxdg,5176
 qpytorch/variational/unwhitened_variational_strategy.py,sha256=068ScAOHk0VHLfkwakR41vrpASqIDjvvnhOFYIEE9uU,10713
 qpytorch/variational/variational_strategy.py,sha256=TD_rPpQL2n7bK869tICT6cA0cc0YFgqi0AsHfyVo2Zc,13155
-qpytorch-0.1.dist-info/LICENSE,sha256=QcK8fAvGl70vlwIHUqKdi4oV_SvhC6lBGYXTR1znTsY,1067
-qpytorch-0.1.dist-info/METADATA,sha256=pOhOSsJjOL6qc4tSYFILwL-ZUN9dKgS4OhbqfjWfDHs,7986
-qpytorch-0.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-qpytorch-0.1.dist-info/top_level.txt,sha256=WZP9m4PVYtj2RhzbzmW4UqUGOy-sOfumPrjnvNFrv4Q,9
-qpytorch-0.1.dist-info/RECORD,,
+qpytorch-0.1.1.dist-info/LICENSE,sha256=QcK8fAvGl70vlwIHUqKdi4oV_SvhC6lBGYXTR1znTsY,1067
+qpytorch-0.1.1.dist-info/METADATA,sha256=9DnPKInL5BeVBkG7vk7XFkUwT_vRSNxyvur0mOIVL54,7499
+qpytorch-0.1.1.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+qpytorch-0.1.1.dist-info/top_level.txt,sha256=WZP9m4PVYtj2RhzbzmW4UqUGOy-sOfumPrjnvNFrv4Q,9
+qpytorch-0.1.1.dist-info/RECORD,,