stationary point

EM’s Convergence in Gaussian Latent Tree Models COLT 2022 Global Convergence and Stability of Stochastic Gradient Descent NeurIPS 2022 Learning a Single Neuron with Adversarial Label Noise via Gradient Descent COLT 2022 Minimax Optimization with Smooth Algorithmic Adversaries ICLR 2022 Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022 Online Nonnegative CP-dictionary Learning for Markovian Data JMLR 2022 On the Convergence of mSGD and AdaGrad for Stochastic Optimization ICLR 2022 On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction AISTATS 2022 Oracle Complexity in Nonsmooth Nonconvex Optimization JMLR 2022 The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions ICLR 2022 The Query Complexity of Local Search and Brouwer in Rounds COLT 2022 Alternating Direction Method of Multipliers for Quantization AISTATS 2021 Analysis of the Optimization Landscape of Linear Quadratic Gaussian (LQG) Control L4DC 2021 Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization NeurIPS 2021 Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization AISTATS 2021 AdaGrad stepsizes: Sharp convergence over nonconvex landscapes JMLR 2020 Complexity of Finding Stationary Points of Nonconvex Nonsmooth Functions ICML 2020 How to Trap a Gradient Flow COLT 2020 On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems ICML 2020 On Stationary-Point Hitting Time and Ergodicity of Stochastic Gradient Langevin Dynamics JMLR 2020 Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations COLT 2020 Statistically Efficient Off-Policy Policy Gradients ICML 2020 The Complexity of Finding Stationary Points with Stochastic Gradient Descent ICML 2020 Efficiently avoiding saddle points with zero order methods: No gradients required NeurIPS 2019 Hessian Aided Policy Gradient ICML 2019