default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDAaron Defazio
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c17]Konstantin Mishchenko, Aaron Defazio:
Prodigy: An Expeditiously Adaptive Parameter-Free Learner. ICML 2024- [c16]Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower:
MoMo: Momentum Models for Adaptive Learning Rates. ICML 2024 - [i32]Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower:
Directional Smoothness and Gradient Methods: Convergence and Adaptivity. CoRR abs/2403.04081 (2024) - [i31]Aaron Defazio, Xingyu Yang, Harsh Mehta, Konstantin Mishchenko, Ahmed Khaled, Ashok Cutkosky:
The Road Less Scheduled. CoRR abs/2405.15682 (2024) - 2023
- [c15]Aaron Defazio, Konstantin Mishchenko:
Learning-Rate-Free Learning by D-Adaptation. ICML 2023: 7449-7479 - [c14]Ashok Cutkosky, Aaron Defazio, Harsh Mehta:
Mechanic: A Learning Rate Tuner. NeurIPS 2023 - [i30]Aaron Defazio, Konstantin Mishchenko:
Learning-Rate-Free Learning by D-Adaptation. CoRR abs/2301.07733 (2023) - [i29]Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower:
MoMo: Momentum Models for Adaptive Learning Rates. CoRR abs/2305.07583 (2023) - [i28]Ashok Cutkosky
, Aaron Defazio, Harsh Mehta:
Mechanic: A Learning Rate Tuner. CoRR abs/2306.00144 (2023) - [i27]Konstantin Mishchenko, Aaron Defazio:
Prodigy: An Expeditiously Adaptive Parameter-Free Learner. CoRR abs/2306.06101 (2023) - [i26]Aaron Defazio, Ashok Cutkosky, Harsh Mehta, Konstantin Mishchenko:
When, Why and How Much? Adaptive Learning Rate Scheduling by Refinement. CoRR abs/2310.07831 (2023) - 2022
- [j3]Aaron Defazio, Mark Tygert, Rachel A. Ward, Jure Zbontar:
Compressed sensing with a jackknife and a bootstrap. J. Data Sci. Stat. Vis. 2(4) (2022) - [j2]Aaron Defazio, Samy Jelassi:
A Momentumized, Adaptive, Dual Averaged Gradient Method. J. Mach. Learn. Res. 23: 144:1-144:34 (2022) - [j1]Aaron Defazio, Léon Bottou:
A scaling calculus for the design and initialization of ReLU networks. Neural Comput. Appl. 34(17): 14807-14821 (2022) - [i25]Aaron Defazio, Baoyu Zhou, Lin Xiao:
Grad-GradaGrad? A Non-Monotone Adaptive Stochastic Gradient Method. CoRR abs/2206.06900 (2022) - 2021
- [c13]Aaron Defazio, Robert M. Gower:
The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization. ACML 2021: 49-64 - [c12]Othmane Sebbouh, Robert M. Gower, Aaron Defazio:
Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball. COLT 2021: 3935-3971 - [i24]Aaron Defazio, Samy Jelassi:
Adaptivity without Compromise: A Momentumized, Adaptive, Dual Averaged Gradient Method for Stochastic Optimization. CoRR abs/2101.11075 (2021) - [i23]Robert M. Gower, Aaron Defazio, Michael G. Rabbat:
Stochastic Polyak Stepsize with a Moving Target. CoRR abs/2106.11851 (2021) - 2020
- [c11]Anuroop Sriram, Jure Zbontar, Tullie Murrell, C. Lawrence Zitnick, Aaron Defazio, Daniel K. Sodickson:
GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction. CVPR 2020: 14303-14310 - [c10]Anuroop Sriram, Jure Zbontar, Tullie Murrell, Aaron Defazio, C. Lawrence Zitnick, Nafissa Yakubova, Florian Knoll, Patricia M. Johnson:
End-to-End Variational Networks for Accelerated MRI Reconstruction. MICCAI (2) 2020: 64-73 - [c9]Aaron Defazio, Tullie Murrell, Michael P. Recht:
MRI Banding Removal via Adversarial Training. NeurIPS 2020 - [i22]Florian Knoll, Tullie Murrell, Anuroop Sriram, Nafissa Yakubova, Jure Zbontar, Michael G. Rabbat, Aaron Defazio, Matthew J. Muckley, Daniel K. Sodickson, C. Lawrence Zitnick, Michael P. Recht:
Advancing machine learning for MR image reconstruction with an open competition: Overview of the 2019 fastMRI challenge. CoRR abs/2001.02518 (2020) - [i21]Aaron Defazio, Tullie Murrell, Michael P. Recht:
MRI Banding Removal via Adversarial Training. CoRR abs/2001.08699 (2020) - [i20]Anuroop Sriram, Jure Zbontar, Tullie Murrell, Aaron Defazio, C. Lawrence Zitnick, Nafissa Yakubova, Florian Knoll, Patricia M. Johnson:
End-to-End Variational Networks for Accelerated MRI Reconstruction. CoRR abs/2004.06688 (2020) - [i19]Aaron Defazio, Robert M. Gower:
Factorial Powers for Stochastic Optimization. CoRR abs/2006.01244 (2020) - [i18]Othmane Sebbouh, Robert M. Gower, Aaron Defazio:
On the convergence of the Stochastic Heavy Ball Method. CoRR abs/2006.07867 (2020) - [i17]Aaron Defazio:
Understanding the Role of Momentum in Non-Convex Optimization: Practical Insights from a Lyapunov Analysis. CoRR abs/2010.00406 (2020) - [i16]Samy Jelassi, Aaron Defazio:
Dual Averaging is Surprisingly Effective for Deep Learning Optimization. CoRR abs/2010.10502 (2020)
2010 – 2019
- 2019
- [c8]Aaron Defazio, Léon Bottou:
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning. NeurIPS 2019: 1753-1763 - [c7]Aaron Defazio:
On the Curved Geometry of Accelerated Optimization. NeurIPS 2019: 1764-1773 - [i15]Aaron Defazio, Léon Bottou:
Scaling Laws for the Principled Design, Initialization and Preconditioning of ReLU Networks. CoRR abs/1906.04267 (2019) - [i14]Anuroop Sriram, Jure Zbontar, Tullie Murrell, C. Lawrence Zitnick, Aaron Defazio, Daniel K. Sodickson:
GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstruction. CoRR abs/1910.12325 (2019) - [i13]Aaron Defazio:
Offset Masking Improves Deep Learning based Accelerated MRI Reconstructions. CoRR abs/1912.01101 (2019) - 2018
- [i12]Jure Zbontar, Florian Knoll, Anuroop Sriram, Matthew J. Muckley, Mary Bruno, Aaron Defazio, Marc Parente, Krzysztof J. Geras, Joe Katsnelson, Hersh Chandarana, Zizhao Zhang, Michal Drozdzal, Adriana Romero, Michael G. Rabbat, Pascal Vincent, James Pinkerton, Duo Wang, Nafissa Yakubova, Erich Owens, C. Lawrence Zitnick, Michael P. Recht, Daniel K. Sodickson, Yvonne W. Lui:
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI. CoRR abs/1811.08839 (2018) - [i11]Aaron Defazio, Léon Bottou:
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning. CoRR abs/1812.04529 (2018) - [i10]Aaron Defazio, Léon Bottou:
Controlling Covariate Shift using Equilibrium Normalization of Weights. CoRR abs/1812.04549 (2018) - [i9]Aaron Defazio:
On the Curved Geometry of Accelerated Optimization. CoRR abs/1812.04634 (2018) - 2016
- [c6]Aaron Defazio:
A Simple Practical Accelerated Method for Finite Sums. NIPS 2016: 676-684 - [i8]Aaron Defazio:
A Simple Practical Accelerated Method for Finite Sums. CoRR abs/1602.02442 (2016) - 2015
- [c5]Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed, Aaron Defazio, Ann Clifton, Anoop Sarkar:
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields. AISTATS 2015 - [i7]Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed, Aaron Defazio, Ann Clifton, Anoop Sarkar:
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields. CoRR abs/1504.04406 (2015) - [i6]Aaron Defazio:
New Optimisation Methods for Machine Learning. CoRR abs/1510.02533 (2015) - 2014
- [c4]Aaron Defazio, Justin Domke, Tibério S. Caetano:
Finito: A faster, permutable incremental gradient method for big data problems. ICML 2014: 1125-1133 - [c3]Aaron Defazio, Francis R. Bach, Simon Lacoste-Julien:
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. NIPS 2014: 1646-1654 - [i5]Aaron Defazio, Francis R. Bach, Simon Lacoste-Julien:
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives. CoRR abs/1407.0202 (2014) - [i4]Aaron J. Defazio, Tibério S. Caetano:
A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation. CoRR abs/1407.2697 (2014) - [i3]Aaron J. Defazio, Tibério S. Caetano, Justin Domke:
Finito: A Faster, Permutable Incremental Gradient Method for Big Data Problems. CoRR abs/1407.2710 (2014) - [i2]Aaron Defazio, Thore Graepel:
A Comparison of learning algorithms on the Arcade Learning Environment. CoRR abs/1410.8620 (2014) - 2012
- [c2]Aaron Defazio, Tibério S. Caetano:
A Graphical Model Formulation of Collaborative Filtering Neighbourhood Methods with Fast Maximum Entropy Training. ICML 2012 - [c1]Aaron Defazio, Tibério S. Caetano:
A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation. NIPS 2012: 1259-1267 - [i1]Aaron Defazio, Tibério S. Caetano:
A Graphical Model Formulation of Collaborative Filtering Neighbourhood Methods with Fast Maximum Entropy Training. CoRR abs/1206.4622 (2012)
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-09-13 01:37 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
