activity
20152023
most citedNon-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields

26 citations · 32 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2023

Optimal Linear Decay Learning Rate Schedules and Further Refinements

Aaron Defazio, Ashok Cutkosky, Harsh Mehta +1

Learning rate schedules used in practice bear little resemblance to those recommended by theory. We close much of this theory/practice gap, and as a consequence are able to derive…

cs.LG2023

Mechanic: A Learning Rate Tuner

Ashok Cutkosky, Aaron Defazio, Harsh Mehta

We introduce a technique for tuning the learning rate scale factor of any base optimization algorithm and schedule automatically, which we call \textsc{mechanic}. Our method provid…

cs.LG2023

Prodigy: An Expeditiously Adaptive Parameter-Free Learner

Konstantin Mishchenko, Aaron Defazio

We consider the problem of estimating the learning rate in adaptive methods, such as AdaGrad and Adam. We propose Prodigy, an algorithm that provably estimates the distance to the…

cs.LG2023

MoMo: Momentum Models for Adaptive Learning Rates

Fabian Schaipp, Ruben Ohana, Michael Eickenberg +2

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type ada…

cs.LG2021

Stochastic Polyak Stepsize with a Moving Target

Robert M. Gower, Aaron Defazio, Michael Rabbat

We propose a new stochastic gradient method called MOTAPS (Moving Targetted Polyak Stepsize) that uses recorded past loss values to compute adaptive stepsizes. MOTAPS can be seen a…

cs.LG2021

Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization

Aaron Defazio, Samy Jelassi

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems fro…