saddle point

Efficient Hyper-parameter Optimization with Cubic Regularization NeurIPS 2023 Escaping saddle points in zeroth-order optimization: the power of two-point estimators ICML 2023 Faster Gradient-Free Methods for Escaping Saddle Points ICLR 2023 Finding Local Minima Efficiently in Decentralized Optimization NeurIPS 2023 HOUDINI: Escaping from Moderately Constrained Saddles IJCAI 2023 Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs NeurIPS 2023 Linear Regularizers Enforce the Strict Saddle Property AAAI 2023 Online Saddle Point Tracking with Decision-Dependent Data L4DC 2023 Randomized Primal-Dual Methods with Adaptive Step Sizes AISTATS 2023 Riemannian stochastic optimization methods avoid strict saddle points NeurIPS 2023 Saddle-to-Saddle Dynamics in Diagonal Linear Networks NeurIPS 2023 AdaGrad Avoids Saddle Points ICML 2022 Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022 Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees NeurIPS 2022 Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima JMLR 2022 Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data NeurIPS 2022 Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning NeurIPS 2022 Faster Perturbed Stochastic Gradient Methods for Finding Local Minima ALT 2022 Lagrangian Method for Q-Function Learning (with Applications to Machine Translation) ICML 2022 Minimax Optimization: The Case of Convex-Submodular AISTATS 2022 Novel Min-Max Reformulations of Linear Inverse Problems JMLR 2022 On Non-local Convergence Analysis of Deep Linear Networks ICML 2022 On the Theoretical Properties of Noise Correlation in Stochastic Optimization NeurIPS 2022 Optimality and Stability in Non-Convex Smooth Games JMLR 2022 Power-Law Escape Rate of SGD ICML 2022