Aaron Defazio
Aaron Defazio
Facebook AI Research
Verified email at anu.edu.au - Homepage
TitleCited byYear
SAGA: A fast incremental gradient method with support for non-strongly convex composite objectives
A Defazio, F Bach, S Lacoste-Julien
Advances in neural information processing systems, 1646-1654, 2014
8112014
Finito: A faster, permutable incremental gradient method for big data problems
A Defazio, J Domke
International Conference on Machine Learning, 1125-1133, 2014
1312014
A simple practical accelerated method for finite sums
A Defazio
Advances in neural information processing systems, 676-684, 2016
612016
Non-uniform stochastic average gradient method for training conditional random fields
M Schmidt, R Babanezhad, M Ahmed, A Defazio, A Clifton, A Sarkar
artificial intelligence and statistics, 819-828, 2015
582015
A convex formulation for learning scale-free networks via submodular relaxation
A Defazio, TS Caetano
Advances in Neural Information Processing Systems, 1250-1258, 2012
342012
fastmri: An open dataset and benchmarks for accelerated mri
J Zbontar, F Knoll, A Sriram, MJ Muckley, M Bruno, A Defazio, M Parente, ...
arXiv preprint arXiv:1811.08839, 2018
212018
A comparison of learning algorithms on the arcade learning environment
A Defazio, T Graepel
arXiv preprint arXiv:1410.8620, 2014
202014
A graphical model formulation of collaborative filtering neighbourhood methods with fast maximum entropy training
A Defazio, T Caetano
arXiv preprint arXiv:1206.4622, 2012
112012
New optimisation methods for machine learning
A Defazio
arXiv preprint arXiv:1510.02533, 2015
92015
On the ineffectiveness of variance reduced optimization for deep learning
A Defazio, L Bottou
arXiv preprint arXiv:1812.04529, 2018
72018
Natural language question answering over triple knowledge bases
A Defazio
Retrieved at, 1-42, 2009
32009
Scaling Laws for the Principled Design, Initialization and Preconditioning of ReLU Networks
A Defazio, L Bottou
arXiv preprint arXiv:1906.04267, 2019
2019
Methods of interpreting error estimates for grayscale image reconstructions
A Defazio, M Tygert
arXiv preprint arXiv:1902.00608, 2019
2019
On the Curved Geometry of Accelerated Optimization
A Defazio
arXiv preprint arXiv:1812.04634, 2018
2018
Controlling Covariate Shift using Equilibrium Normalization of Weights
A Defazio, L Bottou
arXiv preprint arXiv:1812.04549, 2018
2018
How to do A/B testing with early stopping correctly
A Defazio
2016
A COMPLETE GUIDE TO THE BAYES FACTOR TEST
A Defazio
2016
Network Topology Tomography
A Defazio
Australian National University, 2010
2010
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields: Supplementary Material
M Schmidt, R Babanezhad, MO Ahemd, A Defazio, A Clifton, A Sarkar
A convex formulation for learning scale-free networks via submodular relaxation tiberio s. caetano nicta/anu/university of sydney canberra and
AJ Defazio, TS Caetano
The system can't perform the operation now. Try again later.
Articles 1–20