Pith. sign in

REVIEW 1 cited by

On the Convergence of SARAH and Beyond

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 1906.02351 v2 pith:JU7OGDH2 submitted 2019-06-05 cs.LG math.OCstat.ML

classification cs.LGmath.OCstat.ML
keywords problemsepsilonsarahcomplexityconvexsizesteptextbf
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

The main theme of this work is a unifying algorithm, \textbf{L}oop\textbf{L}ess \textbf{S}ARAH (L2S) for problems formulated as summation of $n$ individual loss functions. L2S broadens a recently developed variance reduction method known as SARAH. To find an $\epsilon$-accurate solution, L2S enjoys a complexity of ${\cal O}\big( (n+\kappa) \ln (1/\epsilon)\big)$ for strongly convex problems. For convex problems, when adopting an $n$-dependent step size, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$; while for more frequently adopted $n$-independent step size, the complexity is ${\cal O}(n+ n/\epsilon)$. Distinct from SARAH, our theoretical findings support an $n$-independent step size in convex problems without extra assumptions. For nonconvex problems, the complexity of L2S is ${\cal O}(n+ \sqrt{n}/\epsilon)$. Our numerical tests on neural networks suggest that L2S can have better generalization properties than SARAH. Along with L2S, our side results include the linear convergence of the last iteration for SARAH in strongly convex problems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Variance-Reduced Fast Operator Splitting Methods for Generalized Equations

    math.OC 2025-04 conditional novelty 7.0 of 10

    A new class of accelerated forward-backward and backward-forward splitting methods with variance-reduced estimators achieves O(1/k^2) and o(1/k^2) expected residual convergence for generalized equations under co-coerc...

Pith tools