saddle point

Efficiently testing local optimality and escaping saddles for ReLU networks ICLR 2019 Efficient Nonconvex Empirical Risk Minimization via Adaptive Sample Size Methods AISTATS 2019 Escaping from saddle points on Riemannian manifolds NeurIPS 2019 Escaping Saddle Points with Adaptive Gradient Methods ICML 2019 First-order methods almost always avoid saddle points: The case of vanishing step-sizes NeurIPS 2019 Global Convergence of Gradient Descent for Deep Linear Residual Networks NeurIPS 2019 Heavy-ball Algorithms Always Escape Saddle Points IJCAI 2019 Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers NeurIPS 2019 Non-Asymptotic Pure Exploration by Solving Games NeurIPS 2019 Semi-flat minima and saddle points by embedding neural networks to overparameterization NeurIPS 2019 Sharp Analysis for Nonconvex SGD Escaping from Saddle Points COLT 2019 Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods NeurIPS 2019 Splitting Steepest Descent for Growing Neural Architectures NeurIPS 2019 SSRGD: Simple Stochastic Recursive Gradient Descent for Escaping Saddle Points NeurIPS 2019 Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models NeurIPS 2019 Accelerated Gradient Descent Escapes Saddle Points Faster than Gradient Descent COLT 2018 An Alternative View: When Does SGD Escape Local Minima? ICML 2018 Escaping Saddle Points in Constrained Optimization NeurIPS 2018 Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate ICML 2018 First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time NeurIPS 2018 Stabilizing Adversarial Nets with Prediction Methods ICLR 2018 Stochastic Cubic Regularization for Fast Nonconvex Optimization NeurIPS 2018 Structured Local Minima in Sparse Blind Deconvolution NeurIPS 2018 Third-order Smoothness Helps: Faster Stochastic Optimization Algorithms for Finding Local Minima NeurIPS 2018 TRAINING GENERATIVE ADVERSARIAL NETWORKS VIA PRIMAL-DUAL SUBGRADIENT METHODS: A LAGRANGIAN PERSPECTIVE ON GAN ICLR 2018