Yair Carmon
29 papers · 2017–2026 · 6 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 ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (40) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(18)
👥
Mega-Team · Legion
👑
Triple Crown
🧬
Topic Evolution
📈
Trend Setter
🔥
Unstoppable · Silver
⚡
Prolific Year · Productive
🗃️
Keyword Collector
(121)
💎
Century Club · Bronze
Top co-authors
Research topics
Machine Learning
(26)
Optimization & Theory · Machine Learning
(23)
Mathematics & Optimization
(17)
Optimization
(17)
Artificial Intelligence
(6)
Deep Learning
(5)
Application Areas
(5)
Core AI
(5)
Learning Types · Machine Learning
(4)
Optimization & Theory · Deep Learning
(3)
Natural Language Processing
(2)
Learning Types · Deep Learning
(2)
Core Methods
(1)
Generation
(1)
Learning Paradigms
(1)
Keywords
stochastic convex optimization
(7)
convex optimization
(7)
parameter-free optimization
(4)
gradient descent
(4)
language model
(3)
scaling law
(3)
non-convex optimization
(3)
accelerated gradient
(3)
neural network optimization
(3)
oracle complexity
(3)
regret bound
(3)
lower bound
(2)
distributionally robust optimization
(2)
stochastic gradient descent
(2)
model selection
(2)
sample complexity
(2)
stochastic optimization
(2)
out-of-distribution generalization
(2)
loss landscape
(2)
convex loss
(2)
Papers
Clipping the Price of Adaptivity at the Tail
COLT 2026
The Sample Complexity of Parameter-Free Stochastic Convex Optimization
JMLR 2026
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
Accelerated Parameter-Free Stochastic Optimization
COLT 2024
DataComp-LM: In search of the next generation of training sets for language models
NeurIPS 2024
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
NeurIPS 2024
The Price of Adaptivity in Stochastic Convex Optimization
COLT 2024
DataComp: In search of the next generation of multimodal datasets
NeurIPS 2023
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule
ICML 2023
Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond
ICML 2023
Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds
ICLR 2023
Distributionally Robust Optimization via Ball Oracle Acceleration
NeurIPS 2022
Making SGD Parameter-Free
COLT 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
ICML 2022
Optimal and Adaptive Monteiro-Svaiter Acceleration
NeurIPS 2022
RECAPP: Crafting a More Efficient Catalyst for Convex Optimization
ICML 2022
Scaling Laws Under the Microscope: Predicting Transformer Performance from Small Scale Experiments
EMNLP 2022
Accuracy on the Line: on the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization
ICML 2021
Never Go Full Batch (in Stochastic Convex Optimization)
NeurIPS 2021
Stochastic Bias-Reduced Gradient Methods
NeurIPS 2021
Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss
COLT 2021
Acceleration with a Ball Optimization Oracle
NeurIPS 2020
Large-Scale Methods for Distributionally Robust Optimization
NeurIPS 2020
Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations
COLT 2020
A Rank-1 Sketch for Matrix Multiplicative Weights
COLT 2019
Unlabeled Data Improves Adversarial Robustness
NeurIPS 2019
Variance Reduction for Matrix Games
NeurIPS 2019
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems
NeurIPS 2018
“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions
ICML 2017