critical point

A Generalization Result for Convergence in Learning-to-Optimize ICML 2025 Grokking at the Edge of Linear Separability ICML 2025 On the Geometry and Optimization of Polynomial Convolutional Networks AISTATS 2025 The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks COLT 2025 Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis ICML 2025 Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses AISTATS 2024 A Global Geometric Analysis of Maximal Coding Rate Reduction ICML 2024 Hyperbolic Optimizer as a Dynamical System ICML 2024 The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis JMLR 2024 Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing NeurIPS 2023 Optimal Sets and Solution Paths of ReLU Networks ICML 2023 Quantum speedups for stochastic optimization NeurIPS 2023 Adam Can Converge Without Any Modification On Update Rules NeurIPS 2022 Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape JMLR 2022 Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima JMLR 2022 Non-Convex Bilevel Games with Critical Point Selection Maps NeurIPS 2022 Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022 Embedding Principle of Loss Landscape of Deep Neural Networks NeurIPS 2021 Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021 RMSprop converges with proper hyper-parameter ICLR 2021 Momentum Improves Normalized SGD ICML 2020 Pure and Spurious Critical Points: a Geometric Study of Linear Networks ICLR 2020 Revisiting the Landscape of Matrix Factorization AISTATS 2020 Are deep ResNets provably better than linear predictors? NeurIPS 2019 The Landscape of Non-convex Empirical Risk with Degenerate Population Risk NeurIPS 2019