sgd

A Comprehensive Framework for Analyzing the Convergence of Adam: Bridging the Gap with SGD ICML 2025 A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models ICML 2025 FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training ICML 2025 One-Step Generalization Ratio Guided Optimization for Domain Generalization ICML 2025 On The Concurrence of Layer-wise Preconditioning Methods and Provable Feature Learning ICML 2025 Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization COLT 2025 Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓ_p-Smooth Nonconvex Optimization ICML 2025 SWAN: SGD with Normalization and Whitening Enables Stateless LLM Training ICML 2025 Transformative or Conservative? Conservation laws for ResNets and Transformers ICML 2025 Catapults in SGD: spikes in the training loss and their impact on generalization through feature learning ICML 2024 Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models ICML 2024 Trustless Audits without Revealing Data or Models ICML 2024 Tuning-Free Stochastic Optimization ICML 2024 Uniformly Stable Algorithms for Adversarial Training and Beyond ICML 2024 Visual Transformer with Differentiable Channel Selection: An Information Bottleneck Inspired Approach ICML 2024