Udaya Ghai
11 papers · 2020–2025 · 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze π Conference Polyglot Β· Silver πΊοΈ Taxonomy Completionist (25) π Academic Marathon Β· Sprint π Century Club Β· Bronze
ποΈ
Keyword Collector
(58)
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Trend Setter
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory
(8)
Artificial Intelligence
(5)
Mathematics & Optimization
(5)
Core AI
(5)
Learning Types
(5)
Optimization
(5)
Core Methods
(3)
Reinforcement Learning
(2)
Methods
(2)
Deep Learning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
online learning
(4)
regret minimization
(3)
regret bound
(3)
sample complexity
(2)
model misspecification
(1)
knowledge distillation
(1)
adversarial robustness
(1)
empirical risk minimization
(1)
non-convex optimization
(1)
mirror descent
(1)
kalman filter
(1)
boosting
(1)
gradient descent
(1)
agnostic learning
(1)
matrix completion
(1)
online convex optimization
(1)
neural network optimization
(1)
multiclass learning
(1)
multi-agent control
(1)
adversarial learning
(1)
Papers
How Does Critical Batch Size Scale in Pre-training?
ICLR 2025
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
ICLR 2025
Sample-Optimal Agnostic Boosting with Unlabeled Data
ICML 2025
Sample-Efficient Agnostic Boosting
NeurIPS 2024
Online Nonstochastic Model-Free Reinforcement Learning
NeurIPS 2023
A Regret Minimization Approach to Multi-Agent Control
ICML 2022
Non-convex online learning via algorithmic equivalence
NeurIPS 2022
Robust Online Control with Model Misspecification
L4DC 2022
Generating Adversarial Disturbances for Controller Verification
L4DC 2021
Exponentiated Gradient Meets Gradient Descent
ALT 2020
No-Regret Prediction in Marginally Stable Systems
COLT 2020