Aaron Defazio
Aaron Defazio
Facebook AI Research
Verified email at anu.edu.au - Homepage
Cited by
Cited by
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
Finito: A faster, permutable incremental gradient method for big data problems
A Defazio, J Domke
International Conference on Machine Learning, 1125-1133, 2014
fastMRI: An open dataset and benchmarks for accelerated MRI
J Zbontar, F Knoll, A Sriram, T Murrell, Z Huang, MJ Muckley, A Defazio, ...
arXiv preprint arXiv:1811.08839, 2018
A simple practical accelerated method for finite sums
A Defazio
Advances in neural information processing systems, 676-684, 2016
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
A convex formulation for learning scale-free networks via submodular relaxation
A Defazio, T Caetano
Advances in neural information processing systems 25, 1250-1258, 2012
On the ineffectiveness of variance reduced optimization for deep learning
A Defazio, L Bottou
Advances in Neural Information Processing Systems, 1755-1765, 2019
A comparison of learning algorithms on the arcade learning environment
A Defazio, T Graepel
arXiv preprint arXiv:1410.8620, 2014
fastmri: A publicly available raw k-space and dicom dataset of knee images for accelerated mr image reconstruction using machine learning
F Knoll, J Zbontar, A Sriram, MJ Muckley, M Bruno, A Defazio, M Parente, ...
Radiology: Artificial Intelligence 2 (1), e190007, 2020
A graphical model formulation of collaborative filtering neighbourhood methods with fast maximum entropy training
A Defazio, T Caetano
arXiv preprint arXiv:1206.4622, 2012
New optimisation methods for machine learning
A Defazio
arXiv preprint arXiv:1510.02533, 2015
Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge
F Knoll, T Murrell, A Sriram, N Yakubova, J Zbontar, M Rabbat, A Defazio, ...
Magnetic Resonance in Medicine, 2020
On the curved geometry of accelerated optimization
A Defazio
Advances in Neural Information Processing Systems, 1766-1775, 2019
End-to-End Variational Networks for Accelerated MRI Reconstruction
A Sriram, J Zbontar, T Murrell, A Defazio, CL Zitnick, N Yakubova, F Knoll, ...
arXiv preprint arXiv:2004.06688, 2020
GrappaNet: Combining parallel imaging with deep learning for multi-coil MRI reconstruction
A Sriram, J Zbontar, T Murrell, CL Zitnick, A Defazio, DK Sodickson
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2020
Natural language question answering over triple knowledge bases
A Defazio
Master's thesis, Australian National University, 2009
Scaling laws for the principled design, initialization and preconditioning of relu networks
A Defazio, L Bottou
arXiv preprint arXiv:1906.04267, 2019
Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study
MP Recht, J Zbontar, DK Sodickson, F Knoll, N Yakubova, A Sriram, ...
American Journal of Roentgenology, 1-9, 2020
Dual Averaging is Surprisingly Effective for Deep Learning Optimization
S Jelassi, A Defazio
arXiv preprint arXiv:2010.10502, 2020
Understanding the Role of Momentum in Non-Convex Optimization: Practical Insights from a Lyapunov Analysis
A Defazio
arXiv preprint arXiv:2010.00406, 2020
The system can't perform the operation now. Try again later.
Articles 1–20