Rohith Kuditipudi

I am a PhD student in the computer science department at Stanford University fortunate to be advised by John Duchi and Percy Liang.

I care about improving the security and robustness of machine learning systems, whether via provable guarantees or principled mechanisms for oversight at scale. Recently, I've been thinking about robust statistical estimation and model validation.

Email / Google Scholar / LinkedIn / Twitter

Research

*equal contribution and/or alphabetical ordering

Robust Distortion-free Watermarks for Language Models
Rohith Kuditipudi, John Thickstun, Tatsunori Hashimoto, Percy Liang
arXiv

A Fast Algorithm for Adaptive Private Mean Estimation
John Duchi*, Saminul Haque*, Rohith Kuditipudi*
COLT, 2023 (Best Student Paper Award)
arXiv

Memorize to Generalize: on the Necessity of Interpolation in High Dimensional Linear Regression
Chen Cheng*, John Duchi*, Rohith Kuditipudi*
COLT, 2022
arXiv

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
Rohith Kuditipudi, Xiang Wang, Holden Lee, Yi Zhang, Zhiyuan Li, Wei Hu, Sanjeev Arora, Rong Ge
NeurIPS, 2019
arXiv / talk / blog / code

Minimizing the Number of Detrimental Objects in Multi-Dimensional Graph-Based Codes
Ahmed Hareedy, Rohith Kuditipudi, Robert Calderbank
IEEE TCOM, 2020
arXiv / ITW 19

Learning Two-layer Neural Networks with Symmetric Inputs
Rong Ge*, Rohith Kuditipudi*, Zhize Li*, Xiang Wang*
ICLR, 2019
arXiv

Credit to Jon for the template.