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 language | English |
|---|---|
| Pages (from-to) | 1931-1949 |
| Number of pages | 19 |
| Journal | Proceedings of Machine Learning Research |
| Volume | 267 |
| State | Published - 2025 |
| Event | 42nd 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
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver