Aaron Defazio
19 papers · 2012–2025 · 7 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (29) π Academic Marathon Β· Half π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π
Keyword Champion
π¬
Deep Specialist
(14)
ποΈ
Keyword Collector
(100)
π
Trend Setter
π
Century Club Β· Bronze
π₯
Unstoppable Β· Bronze
Top co-authors
Research topics
Machine Learning
(19)
Optimization & Theory Β· Machine Learning
(17)
Mathematics & Optimization
(12)
Optimization
(12)
Deep Learning
(7)
Optimization & Theory Β· Deep Learning
(5)
Architectures
(3)
Learning Types
(3)
Mathematics
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Healthcare & Medicine
(2)
Application Areas
(2)
Core AI
(2)
Core Methods
(2)
Keywords
convergence rate
(8)
convex optimization
(8)
stochastic gradient descent
(5)
stochastic optimization
(4)
learning rate
(3)
deep learning
(3)
gradient descent
(3)
image reconstruction
(2)
mri reconstruction
(2)
stochastic gradient
(2)
strongly convex
(2)
incremental gradient
(2)
neural network optimization
(2)
non-convex optimization
(2)
variance reduction
(2)
momentum method
(2)
adversarial training
(1)
convergence analysis
(1)
medical imaging
(1)
finite-sum optimization
(1)
Papers
PARQ: Piecewise-Affine Regularized Quantization
ICML 2025
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
NeurIPS 2024
MoMo: Momentum Models for Adaptive Learning Rates
ICML 2024
Prodigy: An Expeditiously Adaptive Parameter-Free Learner
ICML 2024
The Road Less Scheduled
NeurIPS 2024
Learning-Rate-Free Learning by D-Adaptation
ICML 2023
Mechanic: A Learning Rate Tuner
NeurIPS 2023
A Momentumized, Adaptive, Dual Averaged Gradient Method
JMLR 2022
Almost sure convergence rates for Stochastic Gradient Descent and Stochastic Heavy Ball
COLT 2021
The Power of Factorial Powers: New Parameter settings for (Stochastic) Optimization
ACML 2021
GrappaNet: Combining Parallel Imaging With Deep Learning for Multi-Coil MRI Reconstruction
CVPR 2020
MRI Banding Removal via Adversarial Training
NeurIPS 2020
On the Curved Geometry of Accelerated Optimization
NeurIPS 2019
On the Ineffectiveness of Variance Reduced Optimization for Deep Learning
NeurIPS 2019
A Simple Practical Accelerated Method for Finite Sums
NeurIPS 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
NeurIPS 2014
A Convex Formulation for Learning Scale-Free Networks via Submodular Relaxation
NeurIPS 2012