Inertial Newton Algorithms Avoiding Strict Saddle Points

8 November 2021

Papers citing "Inertial Newton Algorithms Avoiding Strict Saddle Points"

8 / 8 papers shown

Title
On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems P. Mertikopoulos Nadav Hallak Ali Kavis Volkan Cevher 48 88 0 19 Jun 2020
Convergence to minima for the continuous version of Backtracking Gradient Descent T. Truong 34 18 0 11 Nov 2019
An Inertial Newton Algorithm for Deep Learning Camille Castera Jérôme Bolte Cédric Févotte Edouard Pauwels PINN ODL 50 63 0 29 May 2019
Understanding the Acceleration Phenomenon via High-Resolution Differential Equations Bin Shi S. Du Michael I. Jordan Weijie J. Su 51 259 0 21 Oct 2018
Backtracking gradient descent method for general $C^1$ functions, with applications to Deep Learning T. Truong T. H. Nguyen 47 10 0 15 Aug 2018
Gradient Descent Only Converges to Minimizers: Non-Isolated Critical Points and Invariant Regions Ioannis Panageas Georgios Piliouras 49 142 0 02 May 2016
A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insights Weijie Su Stephen P. Boyd Emmanuel J. Candes 151 1,166 0 04 Mar 2015
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization Yann N. Dauphin Razvan Pascanu Çağlar Gülçehre Kyunghyun Cho Surya Ganguli Yoshua Bengio ODL 123 1,383 0 10 Jun 2014