The reviewed record of science sign in
Pith

arxiv: 2010.07243 · v2 · pith:4VOQX6F6 · submitted 2020-10-14 · cs.LG · math.OC

Deep Neural Network Training with Frank-Wolfe

Reviewed by Pithpith:4VOQX6F6open to challenge →

classification cs.LG math.OC
keywords stochasticfrank-wolfemethodsneuraltrainingconditionalconstraineddescent
0
0 comments X
read the original abstract

This paper studies the empirical efficacy and benefits of using projection-free first-order methods in the form of Conditional Gradients, a.k.a. Frank-Wolfe methods, for training Neural Networks with constrained parameters. We draw comparisons both to current state-of-the-art stochastic Gradient Descent methods as well as across different variants of stochastic Conditional Gradients. In particular, we show the general feasibility of training Neural Networks whose parameters are constrained by a convex feasible region using Frank-Wolfe algorithms and compare different stochastic variants. We then show that, by choosing an appropriate region, one can achieve performance exceeding that of unconstrained stochastic Gradient Descent and matching state-of-the-art results relying on $L^2$-regularization. Lastly, we also demonstrate that, besides impacting performance, the particular choice of constraints can have a drastic impact on the learned representations.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Training Deep Learning Models with Norm-Constrained LMOs

    cs.LG 2025-02 unverdicted novelty 7.0

    Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.