non-convex optimization

3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation ICML 2022 Accelerated Multiplicative Weights Update Avoids Saddle Points Almost Always IJCAI 2022 Accelerated Projected Gradient Algorithms for Sparsity Constrained Optimization Problems NeurIPS 2022 A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks NeurIPS 2022 AdaGrad Avoids Saddle Points ICML 2022 Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization NeurIPS 2022 A general sample complexity analysis of vanilla policy gradient AISTATS 2022 A gradient sampling method with complexity guarantees for Lipschitz functions in high and low dimensions NeurIPS 2022 A Nonconvex Framework for Structured Dynamic Covariance Recovery JMLR 2022 Approximate Secular Equations for the Cubic Regularization Subproblem NeurIPS 2022 A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization ICML 2022 A Single-timescale Analysis for Stochastic Approximation with Multiple Coupled Sequences NeurIPS 2022 A Stochastic Bundle Method for Interpolation JMLR 2022 Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape JMLR 2022 Asynchronous SGD Beats Minibatch SGD Under Arbitrary Delays NeurIPS 2022 BEER: Fast $O(1/T)$ Rate for Decentralized Nonconvex Optimization with Communication Compression NeurIPS 2022 Better SGD using Second-order Momentum NeurIPS 2022 Black-Box Generalization: Stability of Zeroth-Order Learning NeurIPS 2022 CCCP is Frank-Wolfe in disguise NeurIPS 2022 Communication-Compressed Adaptive Gradient Method for Distributed Nonconvex Optimization AISTATS 2022 Computing D-Stationary Points of $ρ$-Margin Loss SVM AISTATS 2022 Constrained Langevin Algorithms with L-mixing External Random Variables NeurIPS 2022 Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data NeurIPS 2022 Convergence Rates of Non-Convex Stochastic Gradient Descent Under a Generic Lojasiewicz Condition and Local Smoothness ICML 2022 Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems L4DC 2022