The paper investigates variance reduction techniques for non‑convex optimization when gradient evaluations are delayed. It introduces an ordered recursive momentum estimator whose oracle complexity depends on smoothness, variance, and delay, and provides bounds for both stochastic and finite‑sum settings. An asynchronous snapshot variant is also proposed, allowing updates during full‑gradient computations under a completion‑time bound.
arXiv:2502.21099v3 Announce Type: replace-cross Abstract: This paper proposes {\sf AEPG-SPIDER}, an Adaptive Extrapolated Proximal Gradient (AEPG) method with variance reduction for minimizing compos...
arXiv:2610. 13799v1 Announce Type: cross Abstract: Variance reduction improves the convergence rate of stochastic non-convex optimization under the average smoothness condition.
arXiv:2610.07290v1 Announce Type: cross Abstract: Recent advances in penalty-based methods for stochastic bilevel optimization (SBO) have eliminated the need for second-order derivative oracles. Howe...
arXiv:2505.20817v3 Announce Type: replace-cross Abstract: Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees ove...
arXiv:2310. 15976v4 Announce Type: replace Abstract: signSGD is attractive in nonconvex optimization because it communicates sign-valued rather than full-precision gradients.
arXiv:2609. 12785v1 Announce Type: new Abstract: Classical convergence guarantees for stochastic gradient methods typically assume Lipschitz-smooth objectives and finite-variance gradient noise, both frequently violated in practice.
arXiv:2508.16791v2 Announce Type: replace-cross Abstract: We develop a novel past-extragradient-type algorithmic framework, combining both Nesterov's \textit{acceleration} and \textit{variance-reduct...
arXiv:2610.19444v1 Announce Type: cross Abstract: Random reshuffling stochastic gradient descent (RR-SGD) is widely used for finite-sum optimization in machine learning. For convex $L$-smooth compone...
The paper addresses bias introduced by aggregating local signs in distributed sign-based variance reduction methods, which hampers optimal convergence rates. By proposing an unbiased compression of recursive gradient increments to track the global gradient at the server, the authors achieve optimal convergence rates for both nonconvex stochastic and finite-sum optimization. They provide specific rate bounds for α-norms and demonstrate matching sample complexities to centralized settings for finite-sum problems.
arXiv:2609.15723v1 Announce Type: new Abstract: Traditional variance reduction methods (e.g., SPIDER, SARAH, STORM) have been extensively investigated for improving the convergence rates of stochasti...
arXiv:2610. 01599v1 Announce Type: cross Abstract: Stochastic recursive momentum (STORM) achieves fast convergence for nonconvex optimization via the variance reduction effect, but existing analyses rely on the strong average smoothness assumption.
arXiv:2504. 09951v2 Announce Type: replace-cross Abstract: We revisit a classical assumption for analyzing stochastic gradient algorithms where the squared norm of the stochastic subgradient (or the variance for smooth problems) is allowed to grow as fast as the squared norm of the optimization variable.