Skip to content

Matrix-Free Oracle for ExaModels + MathOptAI GrayBox Support #254

@michel2323

Description

@michel2323

MathOptAI's ExaModels extension currently throws an error for GrayBox predictors because ExaModels can't trace opaque functions. Adding VectorNonlinearOracle to ExaModels would materialize jac!/hess! callbacks to full matrices, O(n^2) for a neural network with n inputs. For large NNs, this is prohibitive.

The goal: extend VectorNonlinearOracle with optional jvp!/vjp!/hvp! callbacks. These are O(n) per call (matching torch.func.jvp/vjp/vhp).

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions