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

This presentation covers the ICML 2025 paper: “Faster Stochastic Optimization with Arbitrary Delays via Adaptive Asynchronous Mini-Batching” by Amit Attia, Ofir Gaash, and Tomer Koren. Presented by: Sathvik Reddy & Surya Teja University of Georgia In this presentation, we discuss asynchronous optimization with arbitrary delays, quantile-based delay analysis, asynchronous mini-batching, the proposed algorithms and theoretical results, and the experimental evaluation on Fashion-MNIST. Course Presentation – University of Georgia