Skip to content
conftrace_

saddle point escape

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

non-convex optimization (6) stochastic gradient descent (5) saddle point (4) second-order stationary point (3) distributed optimization (2) federated learning (2) low-rank matrix optimization (1) burer-monteiro decomposition (1) manifold identification (1) hessian-free optimization (1)

Papers

Adaptive Batch Size for Privately Finding Second-Order Stationary Points ICLR 2025 Accelerating Nuclear-norm Regularized Low-rank Matrix Optimization Through Burer-Monteiro Decomposition JMLR 2024 Escaping Saddle Points in Heterogeneous Federated Learning via Distributed SGD with Communication Compression AISTATS 2024 Linear Regularizers Enforce the Strict Saddle Property AAAI 2023 Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning NeurIPS 2022 On the Theoretical Properties of Noise Correlation in Stochastic Optimization NeurIPS 2022 Evolutionary Gradient Descent for Non-convex Optimization IJCAI 2021 Escaping Saddle-Point Faster under Interpolation-like Conditions NeurIPS 2020 A Generic Approach for Escaping Saddle points AISTATS 2018 Escaping Saddles with Stochastic Gradients ICML 2018