stochastic-optimization

Tag

Cards List
#stochastic-optimization

Reducing Per-Sample Harm in Stochastic Optimization

arXiv cs.LG · 9h ago Cached

This paper introduces a framework to reduce per-sample harm in stochastic optimization, where parameter updates from batch averaging and historical states increase individual sample loss. The method uses dimensionality reduction and focuses on the last linear layer for efficiency, showing improved generalization on image classification tasks.

0 favorites 0 likes
#stochastic-optimization

Regularity-Aware Stochastic MGDA with Adaptive Conflict-Avoidant Update Direction Control

arXiv cs.LG · yesterday Cached

This paper proposes a regularity-aware stochastic multi-gradient descent method (MoRe) that adaptively switches between conflict-avoidant and scalarization updates. The method achieves improved convergence rates from O~T^{-1/4} to O~T^{-1/2} in nonconvex settings while maintaining per-iterate conflict avoidance.

0 favorites 0 likes
#stochastic-optimization

MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization

arXiv cs.LG · 2026-06-17 Cached

Proposes MGUP, a momentum-gradient alignment update policy for selective intra-layer parameter updates in stochastic optimization, which integrates with optimizers like AdamW, Lion, and Muon, and provides theoretical convergence guarantees along with superior performance on large-scale model training tasks.

0 favorites 0 likes
#stochastic-optimization

Optimal Gap-Dependent Regret for Private Stochastic Decision-Theoretic Online Learning

arXiv cs.LG · 2026-05-29 Cached

This paper solves a COLT open problem by providing an optimal gap-dependent regret algorithm for private stochastic decision-theoretic online learning, achieving the lower bound of order (log K)/Δ_min + (log K)/ε.

0 favorites 0 likes
#stochastic-optimization

Unified High-Probability Analysis of Stochastic Variance-Reduced Estimation

arXiv cs.LG · 2026-05-18 Cached

This paper presents a unified theoretical framework for stochastic variance-reduced estimation, deriving high-probability bounds via a new Freedman inequality and improving oracle complexities for constrained optimization.

0 favorites 0 likes
#stochastic-optimization

Beyond Bounded Variance: Variance-Reduced Normalized Methods for Nonconvex Optimization under Blum-Gladyshev Noise

arXiv cs.LG · 2026-05-18 Cached

This paper studies nonconvex stochastic optimization under Blum-Gladyshev noise, where gradient variance grows with distance from initialization. It proves convergence guarantees for normalized SGD with momentum and a variance-reduced STORM method, achieving minimax optimal rates under certain conditions.

0 favorites 0 likes
← Back to home

Submit Feedback