Vaishnavh Nagarajan

According to our database, Vaishnavh Nagarajan authored at least 28 papers between 2015 and 2024.

Collaborative distances:

• Dijkstra number of three.
• Erdős number of three.

2024

The pitfalls of next-token prediction.

Gregor Bachmann, Vaishnavh Nagarajan

CoRR, 2024

2023

What do larger image classifiers memorise?

Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar

CoRR, 2023

The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning.

Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite

CoRR, 2023

Think before you speak: Training Language Models With Pause Tokens.

Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan

CoRR, 2023

ResMem: Learn what you can and memorize the rest.

Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

On student-teacher deviations in distillation: does it pay to disobey?

Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Assessing Generalization of SGD via Disagreement.

Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Explaining generalization in deep learning: progress and fundamental limits.

Vaishnavh Nagarajan

CoRR, 2021

Understanding the failure modes of out-of-distribution generalization.

Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur

Proceedings of the 9th International Conference on Learning Representations, 2021

A Learning Theoretic Perspective on Local Explainability.

Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar

Proceedings of the 9th International Conference on Learning Representations, 2021

Provably Safe PAC-MDP Exploration Using Analogies.

Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Lifelong learning in costly feature spaces.

Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan

Theor. Comput. Sci., 2020

2019

Generalization in Deep Networks: The Role of Distance from Initialization.

Vaishnavh Nagarajan, J. Zico Kolter

CoRR, 2019

Uniform convergence may be unable to explain generalization in deep learning.

Vaishnavh Nagarajan, J. Zico Kolter

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience.

Vaishnavh Nagarajan, J. Zico Kolter

Proceedings of the 7th International Conference on Learning Representations, 2019

Revisiting Adversarial Risk.

Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar

Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, 2019

2018

On Adversarial Risk and Training.

Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar

CoRR, 2018

Geriatrix: Aging what you see and what you don't see. A file system aging approach for modern storage systems.

Saurabh Kadekodi, Vaishnavh Nagarajan, Gregory R. Ganger

Proceedings of the 2018 USENIX Annual Technical Conference, 2018

2017

Every team deserves a second chance: an extended study on predicting team performance.

Leandro Soriano Marcolino, Aravind S. Lakshminarayanan, Vaishnavh Nagarajan, Milind Tambe

Auton. Agents Multi Agent Syst., 2017

Gradient descent GAN optimization is locally stable.

Vaishnavh Nagarajan, J. Zico Kolter

Proceedings of the Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 2017

Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems.

Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White

Proceedings of the 30th Conference on Learning Theory, 2017

2016

Learning the best algorithm for max-cut, clustering, and other partitioning problems.

Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White

CoRR, 2016

Incorporating Side Information in Tensor Completion.

Hemank Lamba, Vaishnavh Nagarajan, Kijung Shin, Naji Shajarisales

Proceedings of the 25th International Conference on World Wide Web, 2016

2015

A Reinforcement Learning Approach to Online Learning of Decision Trees.

Abhinav Garlapati, Aditi Raghunathan, Vaishnavh Nagarajan, Balaraman Ravindran

CoRR, 2015

Every Team Deserves a Second Chance: Identifying when Things Go Wrong.

Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe

Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, 2015

Every Team Deserves a Second Chance: An Interactive 9x9 Go Experience (Demonstration).

Leandro Soriano Marcolino, Vaishnavh Nagarajan, Milind Tambe

Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems, 2015

Every Team Makes Mistakes: An Initial Report on Predicting Failure in Teamwork.

Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe

Proceedings of the Learning for General Competency in Video Games, 2015

Every Team Deserves a Second Chance: Identifying When Things Go Wrong (Student Abstract Version).

Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe

Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015