Vaishnavh Nagarajan

49 papers A* 13A 4B 1Journal 26Unranked 5

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Catch Your Breath: Adaptive Computation for Self-Paced Sequence Production. CoRR Alexandre Galashov, Matt Jones, Nan Rosemary Ke, Yuan Cao, Vaishnavh Nagarajan, Michael C. Mozer
2025	J	`jnl`	Deep sequence models tend to memorize geometrically; it is unclear why. CoRR Shahriar Noroozizadeh, Vaishnavh Nagarajan, Elan Rosenfeld, Sanjiv Kumar
2025	A*	`conf`	Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction. ICML Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan
2025	J	`jnl`	Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction. CoRR Vaishnavh Nagarajan, Chen Henry Wu, Charles Ding, Aditi Raghunathan
2024	A*	`conf`	Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning. ICLR Jacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan
2024	J	`jnl`	Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning. CoRR Jacob Mitchell Springer, Vaishnavh Nagarajan, Aditi Raghunathan
2024	A*	`conf`	The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning. ICLR Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
2024	A*	`conf`	The Pitfalls of Next-Token Prediction. ICML Gregor Bachmann, Vaishnavh Nagarajan
2024	J	`jnl`	The pitfalls of next-token prediction. CoRR Gregor Bachmann, Vaishnavh Nagarajan
2024	A*	`conf`	Think before you speak: Training Language Models With Pause Tokens. ICLR Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan
2024	J	`jnl`	What do larger image classifiers memorise? Trans. Mach. Learn. Res. Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
2023	A*	`conf`	On student-teacher deviations in distillation: does it pay to disobey? NeurIPS Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	J	`jnl`	On student-teacher deviations in distillation: does it pay to disobey? CoRR Vaishnavh Nagarajan, Aditya Krishna Menon, Srinadh Bhojanapalli, Hossein Mobahi, Sanjiv Kumar
2023	A*	`conf`	ResMem: Learn what you can and memorize the rest. NeurIPS Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
2023	J	`jnl`	ResMem: Learn what you can and memorize the rest. CoRR Zitong Yang, Michal Lukasik, Vaishnavh Nagarajan, Zonglin Li, Ankit Singh Rawat, Manzil Zaheer, Aditya Krishna Menon, Sanjiv Kumar
2023	J	`jnl`	The Cost of Down-Scaling Language Models: Fact Recall Deteriorates before In-Context Learning. CoRR Tian Jin, Nolan Clement, Xin Dong, Vaishnavh Nagarajan, Michael Carbin, Jonathan Ragan-Kelley, Gintare Karolina Dziugaite
2023	J	`jnl`	Think before you speak: Training Language Models With Pause Tokens. CoRR Sachin Goyal, Ziwei Ji, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar, Vaishnavh Nagarajan
2023	J	`jnl`	What do larger image classifiers memorise? CoRR Michal Lukasik, Vaishnavh Nagarajan, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
2022	A*	`conf`	Assessing Generalization of SGD via Disagreement. ICLR Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter
2021	A*	`conf`	A Learning Theoretic Perspective on Local Explainability. ICLR Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
2021	J	`jnl`	Assessing Generalization of SGD via Disagreement. CoRR Yiding Jiang, Vaishnavh Nagarajan, Christina Baek, J. Zico Kolter
2021	J	`jnl`	Explaining generalization in deep learning: progress and fundamental limits. CoRR Vaishnavh Nagarajan
2021	A	`conf`	Provably Safe PAC-MDP Exploration Using Analogies. AISTATS Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter
2021	A*	`conf`	Understanding the failure modes of out-of-distribution generalization. ICLR Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur
2020	J	`jnl`	A Learning Theoretic Perspective on Local Explainability. CoRR Jeffrey Li, Vaishnavh Nagarajan, Gregory Plumb, Ameet Talwalkar
2020	J	`jnl`	Lifelong learning in costly feature spaces. Theor. Comput. Sci. Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
2020	J	`jnl`	Provably Safe PAC-MDP Exploration Using Analogies. CoRR Melrose Roderick, Vaishnavh Nagarajan, J. Zico Kolter
2020	J	`jnl`	Understanding the Failure Modes of Out-of-Distribution Generalization. CoRR Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur
2019	—	`conf`	Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. ICLR (Poster) Vaishnavh Nagarajan, J. Zico Kolter
2019	J	`jnl`	Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. CoRR Vaishnavh Nagarajan, J. Zico Kolter
2019	J	`jnl`	Generalization in Deep Networks: The Role of Distance from Initialization. CoRR Vaishnavh Nagarajan, J. Zico Kolter
2019	A	`conf`	Revisiting Adversarial Risk. AISTATS Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar
2019	A*	`conf`	Uniform convergence may be unable to explain generalization in deep learning. NeurIPS Vaishnavh Nagarajan, J. Zico Kolter
2019	J	`jnl`	Uniform convergence may be unable to explain generalization in deep learning. CoRR Vaishnavh Nagarajan, J. Zico Kolter
2018	—	`conf`	Geriatrix: Aging what you see and what you don't see. A file system aging approach for modern storage systems. USENIX ATC Saurabh Kadekodi, Vaishnavh Nagarajan, Gregory R. Ganger
2018	J	`jnl`	On Adversarial Risk and Training. CoRR Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar
2017	J	`jnl`	Every team deserves a second chance: an extended study on predicting team performance. Auton. Agents Multi Agent Syst. Leandro Soriano Marcolino, Aravind S. Lakshminarayanan, Vaishnavh Nagarajan, Milind Tambe
2017	—	`conf`	Gradient descent GAN optimization is locally stable. NIPS Vaishnavh Nagarajan, J. Zico Kolter
2017	J	`jnl`	Gradient descent GAN optimization is locally stable. CoRR Vaishnavh Nagarajan, J. Zico Kolter
2017	A*	`conf`	Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems. COLT Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White
2017	B	`conf`	Lifelong Learning in Costly Feature Spaces. ALT Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
2017	J	`jnl`	Lifelong Learning in Costly Feature Spaces. CoRR Maria-Florina Balcan, Avrim Blum, Vaishnavh Nagarajan
2016	—	`conf`	Incorporating Side Information in Tensor Completion. WWW (Companion Volume) Hemank Lamba, Vaishnavh Nagarajan, Kijung Shin, Naji Shajarisales
2016	J	`jnl`	Learning the best algorithm for max-cut, clustering, and other partitioning problems. CoRR Maria-Florina Balcan, Vaishnavh Nagarajan, Ellen Vitercik, Colin White
2015	J	`jnl`	A Reinforcement Learning Approach to Online Learning of Decision Trees. CoRR Abhinav Garlapati, Aditi Raghunathan, Vaishnavh Nagarajan, Balaraman Ravindran
2015	A	`conf`	Every Team Deserves a Second Chance: An Interactive 9x9 Go Experience (Demonstration). AAMAS Leandro Soriano Marcolino, Vaishnavh Nagarajan, Milind Tambe
2015	A*	`conf`	Every Team Deserves a Second Chance: Identifying When Things Go Wrong (Student Abstract Version). AAAI Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe
2015	A	`conf`	Every Team Deserves a Second Chance: Identifying when Things Go Wrong. AAMAS Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe
2015	—	`conf`	Every Team Makes Mistakes: An Initial Report on Predicting Failure in Teamwork. AAAI Workshop: Learning for General Competency in Video Games Vaishnavh Nagarajan, Leandro Soriano Marcolino, Milind Tambe