Skip to content
conftrace_

adaptive gradient algorithm

6 papers

Explore in graph

Also known as

ADAGRAD

Co-occurring keywords · papers mentioning both

smoothness condition (2) proximal point method (2) nesterov acceleration (2) weight decay (2) convergence analysis (2) non-convex optimization (2) optimistic stochastic gradient (1) non-convex stochastic optimization (1) deep network training (1) auxiliary function (1)

Papers

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness ICLR 2025 Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization AISTATS 2025 Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training JMLR 2024 Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions COLT 2023 Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms ICLR 2023 Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets ICLR 2020