conftrace_

saddle point

95 papers

Explore in graph

Also known as

SP

Co-occurring keywords

non-convex optimization (547) stochastic gradient descent (1091) gradient descent (1144) nonconvex optimization (316) second-order stationary point (31) stochastic optimization (1060) convex optimization (1321) local minimum (61) critical point (24) gradient flow (142)

Papers

Minimax Optimization: The Case of Convex-Submodular AISTATS 2022
Distributed Methods with Compressed Communication for Solving Variational Inequalities, with Theoretical Guarantees NIPS 2022
Power-Law Escape Rate of SGD ICML 2022
On the Theoretical Properties of Noise Correlation in Stochastic Optimization NIPS 2022
On Non-local Convergence Analysis of Deep Linear Networks ICML 2022
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022
Lagrangian Method for Q-Function Learning (with Applications to Machine Translation) ICML 2022
AdaGrad Avoids Saddle Points ICML 2022
Faster Perturbed Stochastic Gradient Methods for Finding Local Minima ALT 2022
Optimality and Stability in Non-Convex Smooth Games JMLR 2022
Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems NIPS 2022
Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning NIPS 2022
Novel Min-Max Reformulations of Linear Inverse Problems JMLR 2022
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data NIPS 2022
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum ICML 2022
Escape saddle points by a simple gradient-descent based algorithm NIPS 2021
Direct-Search for a Class of Stochastic Min-Max Problems AISTATS 2021
Fast Extra Gradient Methods for Smooth Structured Nonconvex-Nonconcave Minimax Problems NIPS 2021
Non-attracting Regions of Local Minima in Deep and Wide Neural Networks JMLR 2021
The Effects of Mild Over-parameterization on the Optimization Landscape of Shallow ReLU Neural Networks COLT 2021
A first-order primal-dual method with adaptivity to local smoothness NIPS 2021
Sample Complexity of Policy Gradient Finding Second-Order Stationary Points AAAI 2021
Escaping Saddle Points with Compressed SGD NIPS 2021
Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problems COLT 2020
A Unified Analysis of Extra-gradient and Optimistic Gradient Methods for Saddle Point Problems: Proximal Point Approach AISTATS 2020