saddle point

SGD Can Converge to Local Maxima ICLR 2022 Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022 Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems NeurIPS 2022 A first-order primal-dual method with adaptivity to local smoothness NeurIPS 2021 Byzantine-Resilient Non-Convex Stochastic Gradient Descent ICLR 2021 Direct-Search for a Class of Stochastic Min-Max Problems AISTATS 2021 Escape saddle points by a simple gradient-descent based algorithm NeurIPS 2021 Escaping Saddle Points with Compressed SGD NeurIPS 2021 Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems NeurIPS 2021 Non-attracting Regions of Local Minima in Deep and Wide Neural Networks JMLR 2021 Sample Complexity of Policy Gradient Finding Second-Order Stationary Points AAAI 2021 The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks COLT 2021 A Closer Look at the Optimization Landscapes of Generative Adversarial Networks ICLR 2020 A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach AISTATS 2020 Coarse Correlation in Extensive-Form Games AAAI 2020 Escaping Saddle Points Faster with Stochastic Momentum ICLR 2020 Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems COLT 2020 On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems NeurIPS 2020 Revisiting the Landscape of Matrix Factorization AISTATS 2020 Second Order Optimality in Decentralized Non-Convex Optimization via Perturbed Gradient Tracking NeurIPS 2020 A Tail-Index Analysis of Stochastic Gradient Noise in Deep Neural Networks ICML 2019 Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning ICML 2019 Efficient Dictionary Learning with Gradient Descent ICML 2019 Efficiently avoiding saddle points with zero order methods: No gradients required NeurIPS 2019 Efficiently escaping saddle points on manifolds NeurIPS 2019