API REFERENCE/omnibias-struct

omnibias.struct.torch.tropical

0.1.0a2AlphaPython >=3.10AGPL / commercial

Differentiable dynamic programs for sequences and parses, structured distributions, and finite-temperature bounds.

import omnibias.struct.torch.tropical

Module contract & mathematical conventions

Tropical homotopy twins (torch; theory 01-08).

beta -> inf is temperature collapse, not founding delta -> 0. Do not conflate the two.

Shared formulas do not imply universal floating-point identity. Verify dtype, shape, derivative-order support, and the stated numerical assumptions for the path you use.

Module source ↗Source revision 9a2d73df0573Running reference examples →

FUNCTION

relaxed_value

omnibias.struct.torch.tropical.relaxed_valueSource ↗

relaxed_value(poly: TropicalLinear, x: Tensor, *, beta: float) -> Tensor

The module contract describes the context for this operation. Its signature, explicit validation, return expressions, and implementation are recorded below.

Parameters

Name	Type & default	Contract
polypositional-or-keyword	TropicalLinearRequired	See the operation contract and implementation below.
xpositional-or-keyword	TensorRequired	See the operation contract and implementation below.
betakeyword-only	floatRequired	See the operation contract and implementation below.

ReturnsTensor

Executed regression · g4 parity

Recorded coverage confirms this test executed the API body. This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_g4_parity() -> None:
    pytest.importorskip("jax")
    import jax
    import jax.numpy as jnp
    import torch
    from omnibias.struct.jax.tropical import relaxed_value as rv_jax
    from omnibias.struct.torch.tropical import relaxed_value as rv_torch

    jax.config.update("jax_enable_x64", True)
    poly = _poly()
    x = np.array([[0.1, -0.2], [0.3, 0.4]])
    t = rv_torch(poly, torch.as_tensor(x, dtype=torch.float64), beta=2.0)
    j = rv_jax(poly, jnp.asarray(x, dtype=jnp.float64), beta=2.0)
    np.testing.assert_allclose(t.detach().cpu().numpy(), np.asarray(j), rtol=0.0, atol=1e-12)

python -m pytest "packages/omnibias-struct/tests/test_tropical.py::test_g4_parity" -q

Read the implementation

def relaxed_value(poly: TropicalLinear, x: Tensor, *, beta: float) -> Tensor:
    return logsumexp_beta(scores(poly, x), beta, axis=-1)

Related APIsomnibias.struct.torch.logsumexp_beta↗omnibias.struct.torch.tropical.scores↗

FUNCTION

relaxed_weights

omnibias.struct.torch.tropical.relaxed_weightsSource ↗

relaxed_weights(poly: TropicalLinear, x: Tensor, *, beta: float) -> Tensor

The module contract describes the context for this operation. Its signature, explicit validation, return expressions, and implementation are recorded below.

Parameters

Name	Type & default	Contract
polypositional-or-keyword	TropicalLinearRequired	See the operation contract and implementation below.
xpositional-or-keyword	TensorRequired	See the operation contract and implementation below.
betakeyword-only	floatRequired	See the operation contract and implementation below.

ReturnsTensor

Read the implementation

def relaxed_weights(poly: TropicalLinear, x: Tensor, *, beta: float) -> Tensor:
    return softmax_beta(scores(poly, x), beta, axis=-1)

Related APIsomnibias.struct.torch.softmax_beta↗omnibias.struct.torch.tropical.scores↗

FUNCTION

scores

omnibias.struct.torch.tropical.scoresSource ↗

scores(poly: TropicalLinear, x: Tensor) -> Tensor

The module contract describes the context for this operation. Its signature, explicit validation, return expressions, and implementation are recorded below.

Parameters

Name	Type & default	Contract
polypositional-or-keyword	TropicalLinearRequired	See the operation contract and implementation below.
xpositional-or-keyword	TensorRequired	See the operation contract and implementation below.

ReturnsTensor

Executed regression · g4 parity

Recorded coverage confirms this test executed the API body. This example belongs to the pinned upstream test suite. It may use fixtures and imports from its full file. Run it from that checkout with its test dependencies installed.

Full file, imports & fixtures ↗

def test_g4_parity() -> None:
    pytest.importorskip("jax")
    import jax
    import jax.numpy as jnp
    import torch
    from omnibias.struct.jax.tropical import relaxed_value as rv_jax
    from omnibias.struct.torch.tropical import relaxed_value as rv_torch

    jax.config.update("jax_enable_x64", True)
    poly = _poly()
    x = np.array([[0.1, -0.2], [0.3, 0.4]])
    t = rv_torch(poly, torch.as_tensor(x, dtype=torch.float64), beta=2.0)
    j = rv_jax(poly, jnp.asarray(x, dtype=jnp.float64), beta=2.0)
    np.testing.assert_allclose(t.detach().cpu().numpy(), np.asarray(j), rtol=0.0, atol=1e-12)

python -m pytest "packages/omnibias-struct/tests/test_tropical.py::test_g4_parity" -q

Read the implementation

def scores(poly: TropicalLinear, x: Tensor) -> Tensor:
    m = torch.as_tensor(poly.exponents, dtype=x.dtype, device=x.device)
    a = torch.as_tensor(poly.coeffs, dtype=x.dtype, device=x.device)
    xv = x if x.ndim == 2 else x.unsqueeze(0)
    return a + xv @ m.T

← Package overviewRunnable learning examples →