Praneeth Netrapalli
Research
I work on Gemini at Google DeepMind. At GDM, my work has spanned pre-training, post-training and serving, with current focus specifically on post-training for long horizon tasks. In the past, I have worked on designing reliable and robust machine learning (ML) algorithms, representation learning, nonconvex optimization, stochastic optimization, quantum optimization, and minimax/game-theoretic optimization.
Google Scholar DBLP arXiv
Professional service
PC co-chair for research track of CODS-COMAD 2023.
Editorial Advisory Board of Foundations and Trends in Machine Learning 2024-2026.
Associate Editor for IEEE Transactions on Information Theory 2022-2025.
Area chair/Program committee member for NeurIPS 2019-21, COLT 2019-22, ICLR 2021, ICML 2019 & 2021 and AISTATS 2019.
Selected publications
* indicates alphabetical ordering of author names. Please see here for all publications.
TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving
A. R. Chandra, A. Mahajan, A. Sanyal, M. Wang, S. Chakraborty, S. Chakraborty, S. Chandrasekharan, R. Govindarajan, A. Goyal, J. J. Heckman, Y. Iqbal, D. Jaganathan, S. Kapoor, A. Karch, P. Khandare, S. Krishna, A. Kundu, A. Laddha, T. Lin, S. Maity, N. Mathur, S. N. Meynet, A. Mininno, A. Mishra, V. Niranjan, A. Prakash, P. Rath, D. Roy, D. Sarkar, S. Sastry, G. Shiu, A. Sinha, T. Van Riet, P. Netrapalli and S. Raju
arXiv preprint, 2026
HiRE: High Recall Approximate Top-k Estimation for Efficient LLM Inference
Y. Samaga B L, V. Yerram, C. You, S. Bhojanapalli, S. Kumar, P. Jain and P. Netrapalli
arXiv preprint, 2024
Tandem Transformers for Inference Efficient LLMs
Aishwarya P S, P. A. Nair, Y. Samaga, T. Boyd, S. Kumar, P. Jain and P. Netrapalli
ICML 2024
Minimax Optimization with Smooth Algorithmic Adversaries [*]
T. Fiez, C. Jin, P. Netrapalli and L. Ratliff
ICLR 2022
No quantum speedup over gradient descent for non-smooth convex optimization [*]
A. Garg, R. Kothari, P. Netrapalli and S. Sherif
ITCS 2021
On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
C. Jin, P. Netrapalli, R. Ge, S. M. Kakade and M. I. Jordan
Journal of the ACM (JACM) 2021, Vol. 68, Issue 2, Article 11
The Pitfalls of Simplicity Bias in Neural Networks
H. Shah, K. Tamuly, A. Raghunathan, P. Jain and P. Netrapalli
NeurIPS 2020
Streaming PCA: Matching Matrix Bernstein and Near-Optimal Finite Sample Guarantees for Oja's Algorithm [*]
P. Jain, C. Jin, S. M. Kakade, P. Netrapalli and A. Sidford
COLT 2016
Phase Retrieval using Alternating Minimization
P. Netrapalli, P. Jain and S. Sanghavi
IEEE Transactions on Signal Processing 2015, Vol. 63, Issue 18, Pages 4814–4826
IEEE Signal Processing Society Best Paper Award 2019 (awarded annually to up to six papers published during the previous five years)
Low-rank Matrix Completion using Alternating Minimization [*]
P. Jain, P. Netrapalli and S. Sanghavi
STOC 2013
Contact details
|