activity
20122023
most citedSAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

927 citations · 1.1k across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG201418 cited

A Comparison of learning algorithms on the Arcade Learning Environment

Aaron Defazio, Thore Graepel

Reinforcement learning agents have traditionally been evaluated on small toy problems. With advances in computing power and the advent of the Arcade Learning Environment, it is now…

cs.LG201472 cited

Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems

Aaron J. Defazio, Tibério S. Caetano, Justin Domke

Recent advances in optimization theory have shown that smooth strongly convex finite sums can be minimized faster than by treating them as a black box "batch" problem. In this work…

cs.LG201423 cited

A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation

Aaron J. Defazio, Tiberio S. Caetano

A key problem in statistics and machine learning is the determination of network structure from data. We consider the case where the structure of the graph to be reconstructed is k…

cs.LG2014927 cited

SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

Aaron Defazio, Francis Bach, Simon Lacoste-Julien

In this work we introduce a new optimisation method called SAGA in the spirit of SAG, SDCA, MISO and SVRG, a set of recently proposed incremental gradient algorithms with fast line…

cs.LG201210 cited

A Graphical Model Formulation of Collaborative Filtering Neighbourhood Methods with Fast Maximum Entropy Training

Aaron Defazio, Tiberio Caetano

Item neighbourhood methods for collaborative filtering learn a weighted graph over the set of items, where each item is connected to those it is most similar to. The prediction of…