non-convex optimization

Riemannian stochastic optimization methods avoid strict saddle points NeurIPS 2023 Robust Matrix Sensing in the Semi-Random Model NeurIPS 2023 Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing NeurIPS 2023 SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization ICLR 2023 SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023 Single Point-Based Distributed Zeroth-Order Optimization with a Non-Convex Stochastic Objective Function ICML 2023 SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization NeurIPS 2023 Smoothly Giving up: Robustness for Simple Models AISTATS 2023 Solving a Class of Non-Convex Minimax Optimization in Federated Learning NeurIPS 2023 Solving stochastic weak Minty variational inequalities without increasing batch size ICLR 2023 Special Properties of Gradient Descent with Large Learning Rates ICML 2023 Stability and Generalization of Stochastic Optimization with Nonconvex and Nonsmooth Problems COLT 2023 Stable Nonconvex-Nonconcave Training via Linear Interpolation NeurIPS 2023 STay-ON-the-Ridge: Guaranteed Convergence to Local Minimax Equilibrium in Nonconvex-Nonconcave Games COLT 2023 The Computational Complexity of Finding Stationary Points in Non-Convex Optimization COLT 2023 The Crucial Role of Normalization in Sharpness-Aware Minimization NeurIPS 2023 TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization ICLR 2023 Tight Certification of Adversarially Trained Neural Networks via Nonconvex Low-Rank Semidefinite Relaxations ICML 2023 Time-Independent Information-Theoretic Generalization Bounds for SGLD NeurIPS 2023 Towards Sustainable Learning: Coresets for Data-efficient Deep Learning ICML 2023 Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization NeurIPS 2023 Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization ICLR 2023 Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization NeurIPS 2023 Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top ICLR 2023 Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization NeurIPS 2023