Vaishnavh Nagarajan

Publication Activity (10 Years)

Years Active: 2015-2024
Publications (10 Years): 39

Top Topics

Generalization Bounds

Uniform Convergence

Top Venues

Publications

Jacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning. ICLR (2024)
Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning. ICLR (2024)
Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan
Think before you speak: Training Language Models With Pause Tokens. ICLR (2024)
Gregor Bachmann, Vaishnavh Nagarajan
The pitfalls of next-token prediction. CoRR (2024)
Jacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning. CoRR (2024)
Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
What do larger image classifiers memorise? Trans. Mach. Learn. Res. 2024 (2024)
Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
On student-teacher deviations in distillation: does it pay to disobey? NeurIPS (2023)
Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning. CoRR (2023)
Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan
Think before you speak: Training Language Models With Pause Tokens. CoRR (2023)
Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
ResMem: Learn what you can and memorize the rest. CoRR (2023)
Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
What do larger image classifiers memorise? CoRR (2023)
Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
ResMem: Learn what you can and memorize the rest. NeurIPS (2023)
Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
On student-teacher deviations in distillation: does it pay to disobey? CoRR (2023)
Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter
Assessing Generalization of SGD via Disagreement. ICLR (2022)
Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter
Provably Safe PAC-MDP Exploration Using Analogies. AISTATS (2021)
Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
A Learning Theoretic Perspective on Local Explainability. ICLR (2021)
Vaishnavh Nagarajan
Explaining generalization in deep learning: progress and fundamental limits. CoRR (2021)
Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur
Understanding the failure modes of out-of-distribution generalization. ICLR (2021)
Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter
Assessing Generalization of SGD via Disagreement. CoRR (2021)
Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur
Understanding the Failure Modes of Out-of-Distribution Generalization. CoRR (2020)
Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
A Learning Theoretic Perspective on Local Explainability. CoRR (2020)
Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
Lifelong learning in costly feature spaces. Theor. Comput. Sci. 808 (2020)
Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter
Provably Safe PAC-MDP Exploration Using Analogies. CoRR (2020)
Vaishnavh Nagarajan, J. Zico Kolter
Generalization in Deep Networks: The Role of Distance from Initialization. CoRR (2019)
Vaishnavh Nagarajan, J. Zico Kolter
Uniform convergence may be unable to explain generalization in deep learning. NeurIPS (2019)
Vaishnavh Nagarajan, J. Zico Kolter
Uniform convergence may be unable to explain generalization in deep learning. CoRR (2019)
Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar
Revisiting Adversarial Risk. AISTATS (2019)
Vaishnavh Nagarajan, J. Zico Kolter
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. ICLR (Poster) (2019)
Vaishnavh Nagarajan, J. Zico Kolter
Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. CoRR (2019)
Saurabh Kadekodi, Vaishnavh Nagarajan, Gregory R. Ganger
Geriatrix: Aging what you see and what you don't see. A file system aging approach for modern storage systems. USENIX Annual Technical Conference (2018)
Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar
On Adversarial Risk and Training. CoRR (2018)
Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White
Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems. COLT (2017)
Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
Lifelong Learning in Costly Feature Spaces. CoRR (2017)
Vaishnavh Nagarajan, J. Zico Kolter
Gradient descent GAN optimization is locally stable. CoRR (2017)
Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
Lifelong Learning in Costly Feature Spaces. ALT (2017)
Vaishnavh Nagarajan, J. Zico Kolter
Gradient descent GAN optimization is locally stable. NIPS (2017)
Leandro Soriano Marcolino, Aravind S. Lakshminarayanan, Vaishnavh Nagarajan, Milind Tambe
Every team deserves a second chance: an extended study on predicting team performance. Auton. Agents Multi Agent Syst. 31 (5) (2017)
Hemank Lamba, Vaishnavh Nagarajan, Kijung Shin, Naji Shajarisales
Incorporating Side Information in Tensor Completion. WWW (Companion Volume) (2016)
Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White
Learning the best algorithm for max-cut, clustering, and other partitioning problems. CoRR (2016)
Leandro Soriano Marcolino, Vaishnavh Nagarajan, Milind Tambe
Every Team Deserves a Second Chance: An Interactive 9x9 Go Experience (Demonstration). AAMAS (2015)
Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe
Every Team Deserves a Second Chance: Identifying when Things Go Wrong. AAMAS (2015)
Abhinav Garlapati, Aditi Raghunathan, Vaishnavh Nagarajan, Balaraman Ravindran
A Reinforcement Learning Approach to Online Learning of Decision Trees. CoRR (2015)
Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe
Every Team Makes Mistakes: An Initial Report on Predicting Failure in Teamwork. AAAI Workshop: Learning for General Competency in Video Games (2015)
Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe
Every Team Deserves a Second Chance: Identifying When Things Go Wrong (Student Abstract Version). AAAI (2015)