Skip to main navigation Skip to search Skip to main content

Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching

Research output: Contribution to journal › Conference article › peer-review

Abstract

We consider the problem of asynchronous stochastic optimization, where an optimization algorithm makes updates based on stale stochastic gradients of the objective that are subject to an arbitrary (possibly adversarial) sequence of delays. We present a procedure which, for any given (formula presented), transforms any standard stochastic first-order method to an asynchronous method with convergence guarantee depending on the (formula presented)-quantile delay of the sequence. This approach leads to convergence rates of the form (formula presented) for convex smooth problems, where (formula presented)-quantile delay, generalizing and improving on existing results that depend on the average delay. We further show a method that automatically adapts to all quantiles simultaneously, without any prior knowledge of the delays, achieving convergence rates of the form (formula presented) for convex smooth problems. Our technique is based on asynchronous mini-batching with a careful batchsize selection and filtering of stale gradients.

Original languageEnglish
Pages (from-to)1931-1949
Number of pages19
JournalProceedings of Machine Learning Research
Volume267
StatePublished - 2025
Event42nd International Conference on Machine Learning, ICML 2025 - Vancouver, Canada
Duration: 13 Jul 2025 → 19 Jul 2025

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching'. Together they form a unique fingerprint.

Cite this