openscvx 0.5.3.dev24__tar.gz → 0.5.3.dev25__tar.gz

{openscvx-0.5.3.dev24/openscvx.egg-info → openscvx-0.5.3.dev25}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: openscvx
-Version: 0.5.3.dev24
+Version: 0.5.3.dev25
 Summary: A general Python-based successive convexification implementation which uses a JAX backend.
 Author-email: Chris Hayner and Griffin Norris <haynec@uw.edu>
 License: Apache Software License

{openscvx-0.5.3.dev24 → openscvx-0.5.3.dev25}/docs/UnderTheHood/batching_jit_grad.md

@@ -161,15 +161,27 @@ The batch runs until its slowest element converges or exhausts its own cap;
 finished elements are frozen, not re-iterated, so each element matches the
 corresponding single `solve_jax` run.
 
-**New autotuners batch for free.** An autotuner's tunable knobs follow the
-same derivation: declare them as fields on a `HyperParams` subclass — bare
-annotations, no decorator; subclassing applies the frozen-dataclass transform
-and the JAX pytree registration, and the annotation picks the dtype (`int`
-gets the iteration counter's, `float` the problem's) — assign an instance to
-`self.hyper`, and read `state.hyper.<field>` inside `update_weights` (see the
-`AutotuningBase` docstring). The declaration is the registration — each field
-immediately works as a `solve_jax` override, a `solve_batched` sweep target,
-and a runtime input of the exported artifact, with zero edits anywhere else:
+**Every built-in autotuner knob batches for free.** All numeric knobs of the
+built-in autotuners are declared hyperparameters — the trust-region factors
+(`gamma_1` / `gamma_2`), the acceptance thresholds (`eta_0` / `eta_1` /
+`eta_2`), the weight clips, the cost-relaxation schedule — so any of them is a
+`solve_jax` override and a `solve_batched` sweep target by name:
+
+```python
+# sweep the trust-region growth factor across a batch, one cached artifact
+results = problem.solve_batched(algorithm={"gamma_1": jnp.linspace(1.5, 3.0, B)})
+```
+
+**New autotuners batch the same way.** A custom autotuner's tunable knobs
+follow the same derivation: declare them as fields on a `HyperParams` subclass
+— bare annotations, no decorator; subclassing applies the frozen-dataclass
+transform and the JAX pytree registration, and the annotation picks the dtype
+(`int` gets the iteration counter's, `float` the problem's) — assign an
+instance to `self.hyper`, and read `state.hyper.<field>` inside
+`update_weights` (see the `AutotuningBase` docstring). The declaration is the
+registration — each field immediately works as a `solve_jax` override, a
+`solve_batched` sweep target, and a runtime input of the exported artifact,
+with zero edits anywhere else:
 
 ```python
 from openscvx.algorithms import AutotuningBase, HyperParams

{openscvx-0.5.3.dev24 → openscvx-0.5.3.dev25}/openscvx/_version.py

@@ -18,7 +18,7 @@ version_tuple: tuple[int | str, ...]
 commit_id: str | None
 __commit_id__: str | None
 
-__version__ = version = '0.5.3.dev24'
-__version_tuple__ = version_tuple = (0, 5, 3, 'dev24')
+__version__ = version = '0.5.3.dev25'
+__version_tuple__ = version_tuple = (0, 5, 3, 'dev25')
 
-__commit_id__ = commit_id = 'gba72d9b80'
+__commit_id__ = commit_id = 'ge4b992a50'

{openscvx-0.5.3.dev24 → openscvx-0.5.3.dev25}/openscvx/algorithms/__init__.py

@@ -37,6 +37,8 @@ from typing import Annotated, Any, Dict, List, Optional, Union
 from pydantic import BaseModel, ConfigDict, Field, field_validator
 
 from .autotuner import (
+    AcceptanceRatioAutotuner,
+    AcceptanceRatioHyper,
     AdaptiveProximalWeight,
     AdaptiveProximalWeightSpec,
     AugmentedLagrangian,
@@ -52,6 +54,7 @@ from .base import (
     AlgorithmHistory,
     AlgorithmState,
     AutotuningBase,
+    CandidateIterate,
     DiscretizationResult,
     HyperParams,
     adaptive_state_code_to_str,
@@ -138,6 +141,7 @@ __all__ = [
     "AlgorithmHistory",
     "AlgorithmState",
     "AdaptiveStateCode",
+    "CandidateIterate",
     "adaptive_state_code_to_str",
     "DiscretizationResult",
     "Weights",
@@ -147,6 +151,8 @@ __all__ = [
     "PenalizedTrustRegion",
     "AutotuningBase",
     "HyperParams",
+    "AcceptanceRatioAutotuner",
+    "AcceptanceRatioHyper",
     "AugmentedLagrangian",
     "AdaptiveProximalWeight",
     "ConstantProximalWeight",

{openscvx-0.5.3.dev24 → openscvx-0.5.3.dev25}/openscvx/algorithms/autotuner/__init__.py

@@ -1,11 +1,14 @@
 """SCP weight autotuning strategies."""
 
+from .acceptance_ratio import AcceptanceRatioAutotuner, AcceptanceRatioHyper
 from .adaptive_proximal_weight import AdaptiveProximalWeight, AdaptiveProximalWeightSpec
 from .augmented_lagrangian import AugmentedLagrangian, AugmentedLagrangianSpec
 from .constant_proximal_weight import ConstantProximalWeight, ConstantProximalWeightSpec
 from .ramp_proximal_weight import RampProximalWeight, RampProximalWeightSpec
 
 __all__ = [
+    "AcceptanceRatioAutotuner",
+    "AcceptanceRatioHyper",
     "AdaptiveProximalWeight",
     "AdaptiveProximalWeightSpec",
     "AugmentedLagrangian",

openscvx-0.5.3.dev25/openscvx/algorithms/autotuner/acceptance_ratio.py

@@ -0,0 +1,245 @@
+"""Acceptance-ratio autotuner family.
+
+The acceptance-ratio autotuners share one decision rule: an acceptance ratio
+:math:`\\rho` between the predicted and actual reduction of the nonlinear
+objective drives a four-bucket update of the trust-region weight ``lam_prox``
+(``REJECT`` / ``ACCEPT_HIGHER`` / ``ACCEPT_CONSTANT`` / ``ACCEPT_LOWER``). What
+differs between members is the *multiplier* rule — how the virtual-control and
+virtual-buffer weights (``lam_vc`` / ``lam_vb_*``) respond once an iterate is
+accepted.
+
+:class:`AcceptanceRatioAutotuner` owns the shared decision body and exposes a
+single :meth:`AcceptanceRatioAutotuner._update_multipliers` hook for the
+multiplier rule; subclasses supply only that hook.
+:class:`AdaptiveProximalWeight` is the hook-default (multipliers held
+constant); :class:`AugmentedLagrangian` overrides it with the
+constraint-violation update.
+"""
+
+from typing import TYPE_CHECKING, List
+
+import jax
+import jax.numpy as jnp
+
+from openscvx.config import Config
+from openscvx.utils.printing import (
+    Column,
+    Verbosity,
+    color_acceptance_ratio,
+    color_adaptive_state,
+)
+
+from ..base import AdaptiveStateCode, AutotuningBase, HyperParams
+
+if TYPE_CHECKING:
+    from openscvx.lowered import LoweredJaxConstraints
+
+    from ..base import AlgorithmState, CandidateIterate
+
+
+class AcceptanceRatioHyper(HyperParams):
+    """Knobs shared by every acceptance-ratio autotuner.
+
+    ``lam_cost_drop`` is the iteration after which ``lam_cost`` relaxation
+    applies (``state.k > lam_cost_drop``): ``-1`` relaxes from the first
+    iteration, and the default ``lam_cost_relax=1.0`` makes that a no-op.
+    """
+
+    gamma_1: float = 2.0
+    gamma_2: float = 0.5
+    eta_0: float = 1e-2
+    eta_1: float = 1e-1
+    eta_2: float = 0.8
+    lam_prox_min: float = 1e-3
+    lam_prox_max: float = 1e4
+    lam_cost_drop: int = -1
+    lam_cost_relax: float = 1.0
+
+
+class AcceptanceRatioAutotuner(AutotuningBase):
+    """Four-bucket acceptance-ratio update on ``lam_prox``.
+
+    The acceptance ratio :math:`\\rho` (actual over predicted nonlinear
+    reduction) selects one of four buckets — ``REJECT`` / ``ACCEPT_HIGHER`` /
+    ``ACCEPT_CONSTANT`` / ``ACCEPT_LOWER`` — via a ``jnp.where`` cascade so the
+    whole update traces under ``jax.jit``. Subclasses supply the multiplier
+    rule (how ``lam_vc`` / ``lam_vb_*`` respond on acceptance) through
+    :meth:`_update_multipliers`, and must assign an
+    :class:`AcceptanceRatioHyper` (or subclass) instance to ``self.hyper`` in
+    ``__init__`` — the shared body reads its knobs off ``state.hyper``.
+
+    ``update_weights`` is a pure functional update on the
+    :class:`AlgorithmState` pytree; see the base-class contract.
+    """
+
+    COLUMNS: List[Column] = [
+        Column("J_nonlin", "J_nonlin", 8, "{: .1e}", None, Verbosity.STANDARD),
+        Column("J_lin", "J_lin", 8, "{: .1e}", None, Verbosity.STANDARD),
+        Column("pred_reduction", "pred_red", 9, "{: .1e}", min_verbosity=Verbosity.FULL),
+        Column("actual_reduction", "act_red", 9, "{: .1e}", min_verbosity=Verbosity.FULL),
+        Column(
+            "acceptance_ratio",
+            "acc_ratio",
+            9,
+            "{: .2e}",
+            color_acceptance_ratio,
+            Verbosity.STANDARD,
+        ),
+        Column("lam_prox", "lam_prox", 8, "{: .1e}", min_verbosity=Verbosity.FULL),
+        Column("adaptive_state", "Adaptive", 16, "{}", color_adaptive_state, Verbosity.FULL),
+    ]
+
+    def _update_multipliers(
+        self,
+        state: "AlgorithmState",
+        candidate: "CandidateIterate",
+        nodal_constraints: "LoweredJaxConstraints",
+        params: dict,
+        settings: Config,
+        new_lam_prox: jnp.ndarray,
+    ) -> dict:
+        """Return the multiplier-weight updates to apply on an accepted iterate.
+
+        Each returned entry maps an :class:`AlgorithmState` field name
+        (``lam_vc`` / ``lam_vb_nodal`` / ``lam_vb_cross``) to its updated
+        value, computed against the *candidate* trajectory; the shared body
+        gates each by acceptance (a rejected iterate keeps the previous value).
+        The default holds every multiplier constant — return ``{}``.
+        """
+        return {}
+
+    def update_weights(
+        self,
+        state: "AlgorithmState",
+        candidate: "CandidateIterate",
+        nodal_constraints: "LoweredJaxConstraints",
+        settings: Config,
+        params: dict,
+    ) -> "AlgorithmState":
+        """Return the next-iterate state per the acceptance-ratio rules.
+
+        Pure functional update — see class docstring.
+        """
+        candidate_x_prop = candidate.x_prop_plus[1:]
+        nonlin_cost, nonlin_pen, nodal_pen = self.calculate_nonlinear_penalty(
+            candidate_x_prop,
+            candidate.x,
+            candidate.u,
+            state.lam_vc,
+            state.lam_vb_nodal,
+            state.lam_vb_cross,
+            state.lam_cost,
+            nodal_constraints,
+            params,
+            settings,
+        )
+        J_nonlin = nonlin_cost + nonlin_pen + nodal_pen
+
+        # Cost relaxation: when state.k > hyper.lam_cost_drop, scale
+        # state.lam_cost; otherwise reset to the algorithm's initial weight
+        # (carried on the pytree as state.lam_cost_init, broadcast at
+        # from_settings()). Both constants ride the pytree so per-solve
+        # overrides and vmap sweeps reach the traced body. Scalar
+        # lam_cost_relax preserves the user-specified per-state weight ratios.
+        lam_cost_next = jnp.where(
+            state.k > state.hyper.lam_cost_drop,
+            state.lam_cost * state.hyper.lam_cost_relax,
+            state.lam_cost_init,
+        )
+
+        def first_iter(state):
+            # Iter 1: accept unconditionally, leave weights at their init values,
+            # only refresh trajectory + propagation fields.
+            return state.replace(
+                x=candidate.x,
+                u=candidate.u,
+                x_prop=candidate.x_prop,
+                x_prop_plus=candidate.x_prop_plus,
+                lam_cost=lam_cost_next,
+                J_nonlin=J_nonlin,
+                adaptive_state_code=jnp.asarray(int(AdaptiveStateCode.INITIAL), dtype=jnp.int32),
+            )
+
+        def later_iter(state):
+            # Recompute the previous iterate's J_nonlin from the pytree fields
+            # (state.x/state.u were the *previous* accepted iterate).
+            prev_x_prop = state.x_prop_plus[1:]
+            prev_cost, prev_pen, prev_nodal_pen = self.calculate_nonlinear_penalty(
+                prev_x_prop,
+                state.x,
+                state.u,
+                state.lam_vc,
+                state.lam_vb_nodal,
+                state.lam_vb_cross,
+                state.lam_cost,
+                nodal_constraints,
+                params,
+                settings,
+            )
+            prev_J_nonlin = prev_cost + prev_pen + prev_nodal_pen
+
+            actual = prev_J_nonlin - J_nonlin
+            predicted = prev_J_nonlin - candidate.J_lin
+            # If predicted reduction is exactly zero, force the reject bucket
+            # (rho = -inf) deterministically instead of raising.
+            safe_pred = jnp.where(predicted == 0.0, 1.0, predicted)
+            rho = jnp.where(predicted == 0.0, -jnp.inf, actual / safe_pred)
+
+            is_reject = rho < state.hyper.eta_0
+            is_accept_higher = (rho >= state.hyper.eta_0) & (rho < state.hyper.eta_1)
+            is_accept_constant = (rho >= state.hyper.eta_1) & (rho < state.hyper.eta_2)
+            # is_accept_lower implicit (else)
+            accepted = ~is_reject
+
+            # Compute both lam_prox candidates and gate.
+            lp_higher = jnp.minimum(state.hyper.lam_prox_max, state.hyper.gamma_1 * state.lam_prox)
+            lp_lower = jnp.maximum(state.hyper.lam_prox_min, state.hyper.gamma_2 * state.lam_prox)
+            new_lam_prox = jnp.where(
+                is_reject | is_accept_higher,
+                lp_higher,
+                jnp.where(is_accept_constant, state.lam_prox, lp_lower),
+            )
+
+            # Multiplier (virtual-control / virtual-buffer) updates: computed
+            # against the *candidate* trajectory and gated by `accepted`. Reject
+            # keeps the previous values (so the next subproblem doesn't see a
+            # bumped penalty that wasn't earned). The default hook returns {} —
+            # multipliers held constant.
+            multiplier_updates = self._update_multipliers(
+                state, candidate, nodal_constraints, params, settings, new_lam_prox
+            )
+            gated_multipliers = {
+                name: jnp.where(accepted, value, getattr(state, name))
+                for name, value in multiplier_updates.items()
+            }
+
+            code = jnp.where(
+                is_reject,
+                jnp.int32(AdaptiveStateCode.REJECT),
+                jnp.where(
+                    is_accept_higher,
+                    jnp.int32(AdaptiveStateCode.ACCEPT_HIGHER),
+                    jnp.where(
+                        is_accept_constant,
+                        jnp.int32(AdaptiveStateCode.ACCEPT_CONSTANT),
+                        jnp.int32(AdaptiveStateCode.ACCEPT_LOWER),
+                    ),
+                ),
+            )
+
+            return state.replace(
+                x=jnp.where(accepted, candidate.x, state.x),
+                u=jnp.where(accepted, candidate.u, state.u),
+                x_prop=jnp.where(accepted, candidate.x_prop, state.x_prop),
+                x_prop_plus=jnp.where(accepted, candidate.x_prop_plus, state.x_prop_plus),
+                lam_prox=new_lam_prox,
+                lam_cost=lam_cost_next,
+                J_nonlin=jnp.where(accepted, J_nonlin, state.J_nonlin),
+                predicted_reduction=predicted,
+                actual_reduction=actual,
+                acceptance_ratio=rho,
+                adaptive_state_code=code,
+                **gated_multipliers,
+            )
+
+        return jax.lax.cond(state.k == 1, first_iter, later_iter, state)

openscvx-0.5.3.dev25/openscvx/algorithms/autotuner/adaptive_proximal_weight.py

@@ -0,0 +1,74 @@
+"""Adaptive proximal-weight autotuner.
+
+Same acceptance-ratio decision logic as the rest of the family for
+``lam_prox``, but ``lam_vc`` and ``lam_vb_*`` are held constant at their
+current values — the default multiplier hook.
+"""
+
+from typing import Literal
+
+from pydantic import BaseModel, ConfigDict
+
+from .acceptance_ratio import AcceptanceRatioAutotuner, AcceptanceRatioHyper
+
+
+class AdaptiveProximalWeight(AcceptanceRatioAutotuner):
+    """PTR-style proximal adaptation with fixed virtual-penalty weights.
+
+    Inherits the four-bucket acceptance-ratio update on ``lam_prox`` from
+    :class:`~openscvx.algorithms.autotuner.acceptance_ratio.AcceptanceRatioAutotuner`
+    and keeps the default multiplier hook, so the virtual-control and
+    virtual-buffer weights are carried unchanged.
+
+    ``update_weights`` is a pure functional update on the
+    :class:`AlgorithmState` pytree; see the base-class contract.
+    """
+
+    def __init__(
+        self,
+        gamma_1: float = 2.0,
+        gamma_2: float = 0.5,
+        eta_0: float = 1e-2,
+        eta_1: float = 1e-1,
+        eta_2: float = 0.8,
+        lam_prox_min: float = 1e-3,
+        lam_prox_max: float = 1e4,
+        lam_cost_drop: int = -1,
+        lam_cost_relax: float = 1.0,
+    ):
+        self.hyper = AcceptanceRatioHyper(
+            gamma_1=gamma_1,
+            gamma_2=gamma_2,
+            eta_0=eta_0,
+            eta_1=eta_1,
+            eta_2=eta_2,
+            lam_prox_min=lam_prox_min,
+            lam_prox_max=lam_prox_max,
+            lam_cost_drop=lam_cost_drop,
+            lam_cost_relax=lam_cost_relax,
+        )
+
+
+# =============================================================================
+# Pydantic spec for dict / YAML validation
+# =============================================================================
+
+
+class AdaptiveProximalWeightSpec(BaseModel):
+    """Validates AdaptiveProximalWeight configuration from dict/YAML input."""
+
+    type: Literal["AdaptiveProximalWeight"] = "AdaptiveProximalWeight"
+    gamma_1: float = 2.0
+    gamma_2: float = 0.5
+    eta_0: float = 1e-2
+    eta_1: float = 1e-1
+    eta_2: float = 0.8
+    lam_prox_min: float = 1e-3
+    lam_prox_max: float = 1e4
+    lam_cost_drop: int = -1
+    lam_cost_relax: float = 1.0
+
+    model_config = ConfigDict(extra="forbid")
+
+    def build(self) -> AdaptiveProximalWeight:
+        return AdaptiveProximalWeight(**self.model_dump(exclude={"type"}, exclude_unset=True))