2026
Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGD
ICLR 2026poster
From adversarial robustness to multi-agent learning, many machine learning tasks can be cast as finite-sum min–max optimization or, more generally, as variational inequality problems (VIPs). Owing to their simplicity and scalability, stochastic gradient methods with constant step size are widely us…