Pith. sign in

REVIEW 1 cited by

Stochastic Frank-Wolfe for Composite Convex Minimization

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 1901.10348 v3 pith:RTMGO2O2 submitted 2019-01-29 math.OC cs.AIcs.LGstat.ML

classification math.OCcs.AIcs.LGstat.ML
keywords convexminimizationproblemsaffineconeconstraintsmathcalmethod
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), minimization of a convex function over the positive-semidefinite cone subject to some affine constraints. The majority of classical SDP solvers are designed for the deterministic setting where problem data is readily available. In this setting, generalized conditional gradient methods (aka Frank-Wolfe-type methods) provide scalable solutions by leveraging the so-called linear minimization oracle instead of the projection onto the semidefinite cone. Most problems in machine learning and modern engineering applications, however, contain some degree of stochasticity. In this work, we propose the first conditional-gradient-type method for solving stochastic optimization problems under affine constraints. Our method guarantees $\mathcal{O}(k^{-1/3})$ convergence rate in expectation on the objective residual and $\mathcal{O}(k^{-5/12})$ on the feasibility gap.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Frank-Wolfe with Moreau Envelope Smoothing for Nonsmooth Nonconvex Problems

    math.OC 2026-05 unverdicted novelty 6.0 of 10

    FRAMES uses Moreau envelope smoothing with Frank-Wolfe steps for nonsmooth nonconvex problems, proving convergence rates under mild assumptions and highlighting a new gap relationship.

Pith tools