L4: Practical loss-based stepsize adaptation for deep learning

14 February 2018

Papers citing "L4: Practical loss-based stepsize adaptation for deep learning"

5 / 5 papers shown

Title
An Adaptive Stochastic Gradient Method with Non-negative Gauss-Newton Stepsizes Antonio Orvieto Lin Xiao 30 2 0 05 Jul 2024
Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance Dimitris Oikonomou Nicolas Loizou 38 4 0 06 Jun 2024
Amortized Proximal Optimization Juhan Bae Paul Vicol Jeff Z. HaoChen Roger C. Grosse ODL 15 14 0 28 Feb 2022
KOALA: A Kalman Optimization Algorithm with Loss Adaptivity A. Davtyan Sepehr Sameni L. Cerkezi Givi Meishvili Adam Bielski Paolo Favaro ODL 36 2 0 07 Jul 2021
LOSSGRAD: automatic learning rate in gradient descent B. Wójcik Lukasz Maziarka Jacek Tabor ODL 17 4 0 20 Feb 2019