[Feature Request] Levenberg Marquardt

[mizu-bai]

Feature

Implementation of Levenberg Marquardt optimizer.

Motivation

In MATLAB, the feedforwardnet supports many optimizers, and some are not implemented in PyTorch, such as trainlm (Levenberg Marquardt). From tests from our gourp and others, Levenberg Marquardt performs much better and needs less epochs to coverage than first-order optimizers (Adam, SGD with Momentum) on regression model. Some issues in PyTorch issue list hope for a implementation of Levenverg Marquardt algorithm, but there are no more reponse. It will be helpful to implement the Levenberg Marquardt optimizer and I am willing to help test.

Addition

Here are some helpful information and codes.

• An introduction on Wikipedia. Levenberg–Marquardt algorithm
• An implementation for Tensorflow. tf-levenberg-marquardt

[Felix Dangel]

Hi,

interesting suggestion. Do you have a specific use case where first-order methods don't work for example? BackPACK certainly provides the functionality to implement such an optimizer, and I would be happy to help out in case of issues.