Skip to main content
API REFERENCE/omnibias-convex

omnibias.convex.jax

0.1.0a2AlphaPython >=3.10AGPL / commercial

Differentiable LP and QP solver paths, barrier methods, KKT sensitivities, and scoped optimality evidence.

import omnibias.convex.jax
Module contract & mathematical conventions

JAX backend for omnibias-convex.

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 →
layerModule ↗penaltyModule ↗solverModule ↗

Imports & aliases​

These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.

Import from this moduleCanonical reference
InfeasibleProblemErroromnibias.convex.jax.InfeasibleProblemError
lp_layeromnibias.convex.jax.lp_layer
penalty_descentomnibias.convex.jax.penalty_descent
penalty_gradientomnibias.convex.jax.penalty_gradient
qp_layeromnibias.convex.jax.qp_layer
solve_lpomnibias.convex.jax.solve_lp
solve_lp_penaltyomnibias.convex.jax.solve_lp_penalty
solve_qpomnibias.convex.jax.solve_qp
solve_qp_penaltyomnibias.convex.jax.solve_qp_penalty
← Package overviewRunnable learning examples →