Vaishnavh Nagarajan
17 papers · 2017–2025 · 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 ↓+5 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (30) π Academic Marathon Β· Sprint π£ Hot Topic Early Bird
π
Conference Pioneer
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(75)
Top co-authors
Research topics
Machine Learning
(15)
Optimization & Theory
(13)
Artificial Intelligence
(6)
Core AI
(6)
Core Methods
(6)
Learning Types
(5)
Deep Learning
(3)
Natural Language Processing
(3)
Generation
(3)
Application Areas
(2)
Mathematics & Optimization
(1)
Reinforcement Learning
(1)
Architectures
(1)
Methods
(1)
Models
(1)
Keywords
gradient descent
(4)
generalization bound
(4)
stochastic gradient descent
(2)
out-of-distribution generalization
(2)
neural network optimization
(2)
implicit bia
(2)
domain generalization
(1)
sample efficiency
(1)
learning theory
(1)
in-context learning
(1)
question answering
(1)
sample complexity
(1)
transformer
(1)
sharpness-aware minimization
(1)
uniform convergence
(1)
knowledge distillation
(1)
nearest neighbor
(1)
model calibration
(1)
deep learning
(1)
ensemble learning
(1)
Papers
Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction
ICML 2025
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
ICLR 2024
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
ICLR 2024
The Pitfalls of Next-Token Prediction
ICML 2024
Think before you speak: Training Language Models With Pause Tokens
ICLR 2024
On student-teacher deviations in distillation: does it pay to disobey?
NeurIPS 2023
ResMem: Learn what you can and memorize the rest
NeurIPS 2023
Assessing Generalization of SGD via Disagreement
ICLR 2022
A Learning Theoretic Perspective on Local Explainability
ICLR 2021
Provably Safe PAC-MDP Exploration Using Analogies
AISTATS 2021
Understanding the failure modes of out-of-distribution generalization
ICLR 2021
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience
ICLR 2019
Revisiting Adversarial Risk
AISTATS 2019
Uniform convergence may be unable to explain generalization in deep learning
NeurIPS 2019
Gradient descent GAN optimization is locally stable
NeurIPS 2017
Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
COLT 2017
Lifelong Learning in Costly Feature Spaces
ALT 2017