Pith. sign in

REVIEW 2 cited by

Deep Neural Network Training with Frank-Wolfe

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

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

classification cs.LGmath.OC
keywords stochasticfrank-wolfemethodsneuraltrainingconditionalconstraineddescent
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise

    math.OC 2025-06 reject novelty 6.0 of 10

    Lion and Muon with weight decay are shown to be instances of one stochastic Frank-Wolfe algorithm, and clipped and variance-reduced variants get the first high-probability convergence rates for nonconvex Frank-Wolfe u...

  2. prunAdag: an adaptive pruning-aware gradient method

    math.OC 2025-02 conditional novelty 6.0 of 10

    prunAdag separates parameters into optimisable and decreasable sets, updates them with Adagrad-like rules, and provably drives the average gradient norm to zero at rate O(log(k)/sqrt(k+1)).

Pith tools