Aaron Defazio
19 papers · 2012–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🐣 Hot Topic Early Bird 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) 🏃 Academic Marathon (13)
🏃
Academic Marathon
(13)
🐣
Hot Topic Early Bird
🐝
Cross-Pollinator
(7)
🔬
Deep Specialist
(11)
🗃️
Keyword Collector
(77)
💎
Century Club
(19)
🔥
Unstoppable
(7)
📈
Trend Setter
Conferences
NIPS (9)
ICML (5)
ACML (1)
AISTATS (1)
COLT (1)
CVPR (1)
JMLR (1)
Top co-authors
Research topics
Keywords
convex optimization
(8)
stochastic gradient descent
(5)
convergence rate
(5)
stochastic optimization
(4)
gradient descent
(3)
deep learning
(3)
neural network optimization
(2)
stochastic gradient
(2)
image reconstruction
(2)
variance reduction
(2)
momentum method
(2)
strongly convex
(2)
learning rate
(2)
incremental gradient
(2)
mri reconstruction
(2)
adversarial training
(1)
non-convex optimization
(1)
medical imaging
(1)
network reconstruction
(1)
structure learning
(1)
Papers
PARQ: Piecewise-Affine Regularized Quantization
ICML 2025
The Road Less Scheduled
NIPS 2024
MoMo: Momentum Models for Adaptive Learning Rates
ICML 2024
Prodigy: An Expeditiously Adaptive Parameter-Free Learner
ICML 2024
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
NIPS 2024
Learning-Rate-Free Learning by D-Adaptation
ICML 2023
Mechanic: A Learning Rate Tuner
NIPS 2023
A Momentumized, Adaptive, Dual Averaged Gradient Method
JMLR 2022
The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization
ACML 2021
Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball
COLT 2021
GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction
CVPR 2020
MRI Banding Removal via Adversarial Training
NIPS 2020
On the Curved Geometry of Accelerated Optimization
NIPS 2019
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
NIPS 2019
A Simple Practical Accelerated Method for Finite Sums
NIPS 2016
Non-Uniform Stochastic Average Gradient Method for Training Conditional Random Fields
AISTATS 2015
Finito: A faster, permutable incremental gradient method for big data problems
ICML 2014
SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives
NIPS 2014
A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation
NIPS 2012