Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization

7 February 2020

Papers citing "Low Rank Saddle Free Newton: A Scalable Method for Stochastic Nonconvex Optimization"

5 / 5 papers shown

Title
PETScML: Second-order solvers for training regression problems in Scientific Machine Learning Stefano Zampini Umberto Zerbinati George Turkyyiah David E. Keyes 40 4 0 18 Mar 2024
Series of Hessian-Vector Products for Tractable Saddle-Free Newton Optimisation of Neural Networks E. T. Oldewage Ross M. Clarke José Miguel Hernández-Lobato ODL 17 1 0 23 Oct 2023
Residual-based error correction for neural operator accelerated infinite-dimensional Bayesian inverse problems Lianghao Cao Thomas O'Leary-Roseberry Prashant K. Jha J. Oden Omar Ghattas 25 26 0 06 Oct 2022
Learning High-Dimensional Parametric Maps via Reduced Basis Adaptive Residual Networks Thomas O'Leary-Roseberry Xiaosong Du A. Chaudhuri J. Martins Karen E. Willcox Omar Ghattas 30 22 0 14 Dec 2021
First-order Methods Almost Always Avoid Saddle Points J. Lee Ioannis Panageas Georgios Piliouras Max Simchowitz Michael I. Jordan Benjamin Recht ODL 93 82 0 20 Oct 2017