| 2025 | ICML | PARQ: Piecewise-Affine Regularized Quantization. | Lisa Jin, Jianhao Ma, Zechun Liu, Andrey Gromov, Aaron Defazio, Lin Xiao |
| 2024 | ICML | Prodigy: An Expeditiously Adaptive Parameter-Free Learner. | Konstantin Mishchenko, Aaron Defazio |
| 2024 | ICML | MoMo: Momentum Models for Adaptive Learning Rates. | Fabian Schaipp, Ruben Ohana, Michael Eickenberg, Aaron Defazio, Robert M. Gower |
| 2023 | ICML | Learning-Rate-Free Learning by D-Adaptation. | Aaron Defazio, Konstantin Mishchenko |
| 2021 | ACML | The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization. | Aaron Defazio, Robert M. Gower |
| 2021 | COLT | Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball. | Othmane Sebbouh, Robert M. Gower, Aaron Defazio |
| 2020 | CVPR | GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction. | Anuroop Sriram, Jure Zbontar, Tullie Murrell, C. Lawrence Zitnick, Aaron Defazio, Daniel K. Sodickson |
| 2020 | MICCAI | End-to-End Variational Networks for Accelerated MRI Reconstruction. | Anuroop Sriram, Jure Zbontar, Tullie Murrell, Aaron Defazio, C. Lawrence Zitnick, Nafissa Yakubova, Florian Knoll, Patricia M. Johnson |
| 2015 | AISTATS | Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields. | Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed, Aaron Defazio, Ann Clifton, Anoop Sarkar |
| 2014 | ICML | Finito: A faster, permutable incremental gradient method for big data problems. | Aaron Defazio, Justin Domke, Tibrio S. Caetano |
| 2012 | ICML | A Graphical Model Formulation of Collaborative Filtering Neighbourhood Methods with Fast Maximum Entropy Training. | Aaron Defazio, Tibrio S. Caetano |