2026
High-Probability Bounds for the Last Iterate of Clipped SGD
ICLR 2026poster
We study the problem of minimizing a convex objective when only noisy gradient estimates are available. Under the mild assumption that the stochastic gradients have finite $\alpha$-th moments for some $\alpha \in (1,2]$, we show that the last iterate of clipped stochastic gradient descent (Clipped-S…