conftrace_

critical point

24 papers

Explore in graph

Co-occurring keywords

non-convex optimization (547) saddle point (95) loss landscape (149) stochastic gradient descent (1091) matrix sensing (24) convergence rate (607) neural network optimization (1293) convergence analysis (395) matrix factorization (529) nonconvex optimization (316)

Papers

The Loss Landscape of Deep Linear Neural Networks: a Second-order Analysis JMLR 2024
Absence of spurious solutions far from ground truth: A low-rank analysis with high-order losses AISTATS 2024
Optimal Sets and Solution Paths of ReLU Networks ICML 2023
Quantum speedups for stochastic optimization NIPS 2023
Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing NIPS 2023
Non-Convex Bilevel Games with Critical Point Selection Maps NIPS 2022
Adam Can Converge Without Any Modification On Update Rules NIPS 2022
Distributed Stochastic Gradient Descent: Nonconvexity, Nonsmoothness, and Convergence to Local Minima JMLR 2022
Three-stage Evolution and Fast Equilibrium for SGD with Non-degerate Critical Points ICML 2022
Asymptotic Study of Stochastic Adaptive Algorithms in Non-convex Landscape JMLR 2022
Embedding Principle of Loss Landscape of Deep Neural Networks NIPS 2021
Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances ICML 2021
Revisiting the Landscape of Matrix Factorization AISTATS 2020
Momentum Improves Normalized SGD ICML 2020
Are deep ResNets provably better than linear predictors? NIPS 2019
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk NIPS 2019
Convergence guarantees for a class of non-convex and non-smooth optimization problems ICML 2018
Optimization Landscape and Expressivity of Deep CNNs ICML 2018
Geometry of Neural Network Loss Surfaces via Random Matrix Theory ICML 2017
How regularization affects the critical points in linear networks NIPS 2017
On the Flatness of Loss Surface for Two-layered ReLU Networks ACML 2017
A New Theory for Matrix Completion NIPS 2017
Accelerated Proximal Gradient Methods for Nonconvex Programming NIPS 2015
Open Problem: The landscape of the loss surfaces of multilayer networks COLT 2015