Sotabase

Career

· Member Of Technical Staff, OpenAI2025–
· Research Scientist, Meta2023–2025
· Postdoctoral Researcher, Stanford University Department of Computer Science2021–2023
· Research Intern, Google2019–2019
· Doctor of Philosophy - PhD, Physics, University of California, Berkeley2015–2021
· Graduate Research Assistant, University of California, Berkeley2015–2021
· BTech+MTech, Engineering Physics, Indian Institute of Technology, Bombay2010–2015

Publications (68)

The Llama 3 Herd of Models
2024
12,282
cited
On the Opportunities and Risks of Foundation Models
arXiv.org · 2021
5,795
cited
Holistic Evaluation of Language Models
Trans. Mach. Learn. Res. · 2023
1,324
cited
Underdamped Langevin MCMC: A non-asymptotic analysis
Annual Conference Computational Learning Theory · 2017
322
cited
Proving Test Set Contamination in Black Box Language Models
International Conference on Learning Representations · 2023
201
cited
Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting
arXiv.org · 2018
173
cited
When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards
Annual Meeting of the Association for Computational Linguistics · 2024
119
cited
Finite-sample analysis of interpolating linear classifiers in the overparameterized regime
Journal of machine learning research · 2020
114
cited
Is there an analog of Nesterov acceleration for gradient-based MCMC?
2021
97
cited
Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
Annual Conference Computational Learning Theory · 2022
89
cited
On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
International Conference on Machine Learning · 2018
87
cited
Is There an Analog of Nesterov Acceleration for MCMC?
arXiv.org · 2019
79
cited
The intriguing role of module criticality in the generalization of deep networks
International Conference on Learning Representations · 2019
57
cited
Langevin Monte Carlo without Smoothness
International Conference on Artificial Intelligence and Statistics · 2019
48
cited
OSOM: A Simultaneously Optimal Algorithm for Multi-Armed and Linear Contextual Bandits
International Conference on Artificial Intelligence and Statistics · 2019
48
cited
Multilingual Machine Translation with Open Large Language Models at Practical Scale: An Empirical Study
North American Chapter of the Association for Computational Linguistics · 2025
36
cited
Random Feature Amplification: Feature Learning and Generalization in Neural Networks
Journal of machine learning research · 2022
33
cited
On the Theory of Reinforcement Learning with Once-per-Episode Feedback
Neural Information Processing Systems · 2021
32
cited
Alternating minimization for dictionary learning with random initialization
Neural Information Processing Systems · 2017
28
cited
Enhancement of Spin-transfer torque switching via resonant tunneling
2014
28
cited
Sotabase
Niladri Chatterji | Researcher Profile | Sotabase | Sotabase