Regularized Newton Method with Global $O(1/k^2)$ Convergence

v1v2v3 (latest)

Regularized Newton Method with Global $O(1/k^2)$ Convergence

3 December 2021

Konstantin Mishchenko

ArXiv (abs)PDF HTML

Papers citing "Regularized Newton Method with Global $O(1/k^2)$ Convergence"

9 / 9 papers shown

Title
Gradient Norm Regularization Second-Order Algorithms for Solving Nonconvex-Strongly Concave Minimax Problems Jun-Lin Wang Zi Xu 131 1 0 24 Nov 2024
Minimizing Quasi-Self-Concordant Functions by Gradient Regularization of Newton Method N. Doikov 71 7 0 28 Aug 2023
Rethinking Gauss-Newton for learning over-parameterized models Michael Arbel Romain Menegaux Pierre Wolinski AI4CE 60 6 0 06 Feb 2023
Second-order optimization with lazy Hessians N. Doikov El Mahdi Chayti Martin Jaggi 62 17 0 01 Dec 2022
Extra-Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods Kimon Antonakopoulos Ali Kavis Volkan Cevher ODL 86 12 0 03 Nov 2022
Super-Universal Regularized Newton Method N. Doikov Konstantin Mishchenko Y. Nesterov 51 32 0 11 Aug 2022
FedNew: A Communication-Efficient and Privacy-Preserving Newton-Type Method for Federated Learning Anis Elgabli Chaouki Ben Issaid Amrit Singh Bedi K. Rajawat M. Bennis Vaneet Aggarwal FedML 73 34 0 17 Jun 2022
The First Optimal Acceleration of High-Order Methods in Smooth Convex Optimization D. Kovalev Alexander Gasnikov 76 31 0 19 May 2022
Newton-MR: Inexact Newton Method With Minimum Residual Sub-problem Solver Fred Roosta Yang Liu Peng Xu Michael W. Mahoney 43 15 0 30 Sep 2018