Demon: Improved Neural Network Training with Momentum Decay

Demon: Improved Neural Network Training with Momentum Decay

11 October 2019

Cameron R. Wolfe

Anastasios Kyrillidis

Papers citing "Demon: Improved Neural Network Training with Momentum Decay"

5 / 5 papers shown

Title
Better Schedules for Low Precision Training of Deep Neural Networks Cameron R. Wolfe Anastasios Kyrillidis 45 1 0 04 Mar 2024
FAIR-FATE: Fair Federated Learning with Momentum Teresa Salazar Miguel X. Fernandes Helder Araújo Pedro Abreu FedML 32 18 0 27 Sep 2022
Quasi-hyperbolic momentum and Adam for deep learning Jerry Ma Denis Yarats ODL 76 129 0 16 Oct 2018
GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding Alex Jinpeng Wang Amanpreet Singh Julian Michael Felix Hill Omer Levy Samuel R. Bowman ELM 297 6,956 0 20 Apr 2018
A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay L. Smith 205 1,019 0 26 Mar 2018