Pith. sign in

REVIEW 2 cited by

Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients

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 2404.14758 v1 pith:RPQF4QTC submitted 2024-04-23 math.OC cs.LGstat.ML

classification math.OCcs.LGstat.ML
keywords mini-batchsizealphahessianvariance-reducedapproximationgradientmb-svrn
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We show that, for finite-sum minimization problems, incorporating partial second-order information of the objective function can dramatically improve the robustness to mini-batch size of variance-reduced stochastic gradient methods, making them more scalable while retaining their benefits over traditional Newton-type approaches. We demonstrate this phenomenon on a prototypical stochastic second-order algorithm, called Mini-Batch Stochastic Variance-Reduced Newton ($\texttt{Mb-SVRN}$), which combines variance-reduced gradient estimates with access to an approximate Hessian oracle. In particular, we show that when the data size $n$ is sufficiently large, i.e., $n\gg \alpha^2\kappa$, where $\kappa$ is the condition number and $\alpha$ is the Hessian approximation factor, then $\texttt{Mb-SVRN}$ achieves a fast linear convergence rate that is independent of the gradient mini-batch size $b$, as long $b$ is in the range between $1$ and $b_{\max}=O(n/(\alpha \log n))$. Only after increasing the mini-batch size past this critical point $b_{\max}$, the method begins to transition into a standard Newton-type algorithm which is much more sensitive to the Hessian approximation quality. We demonstrate this phenomenon empirically on benchmark optimization tasks showing that, after tuning the step size, the convergence rate of $\texttt{Mb-SVRN}$ remains fast for a wide range of mini-batch sizes, and the dependence of the phase transition point $b_{\max}$ on the Hessian approximation factor $\alpha$ aligns with our theoretical predictions.

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. SAPPHIRE: Preconditioned Stochastic Variance Reduction for Faster Large-Scale Statistical Learning

    stat.ML 2025-01 conditional novelty 6.0 of 10

    SAPPHIRE is a new preconditioned variance-reduced stochastic method with provable linear convergence for composite convex problems, achieving large speedups on regularized ERM.

  2. Design Criteria for SGD Preconditioners: Local Conditioning, Noise Floors, and Basin Stability

    math.NA 2025-11 conditional novelty 3.0 of 10

    The late-stage noise floor of preconditioned SGD is the product of the M-metric condition number and the preconditioned noise level, so the design goal is to improve conditioning while dampening noise.

Pith tools