Dhruv Sarkar

Marina Bay, Singapore

January 2026

Durga Puja, Kolkata, India

October 2025

I am a graduate student at the Massachusetts Institute of Technology, where I am advised by Prof. Ramesh Raskar. I am broadly interested in building principled learning systems that can make reliable decisions, adapt through interaction, and align with human objectives.

Prior to this I was a CS undergraduate at the Indian Institute of Technology Kharagpur, where I worked on the theoretical foundations of Machine Learning and Reinforcement Learning. I was fortunate to be advised by Prof. Abhishek Sinha and Prof. Sayak Ray Chowdhury. I also had the opportunity to work with Prof. Vaneet Aggarwal.

Recruiting

I am actively seeking strong undergraduate researchers to collaborate with. MIT undergraduates interested in my work are encouraged to reach out. I am also open to remotely mentoring exceptionally strong external undergraduates (e.g., top IITs or equivalent) with rigorous backgrounds in CS, EE, or Mathematics. Please send your CV and a brief summary of your interests.

Get in touch

news

Sep 15, 2026	I joined the MIT Media Lab as a graduate student advised by Prof. Ramesh Raskar.
Jun 12, 2026	New preprint with Prof. Vaneet Aggarwal: Nonlinear Two-Time-Scale Stochastic Approximation: A Sharp Phase Transition and How to Beat It.
May 20, 2026	New preprint with Prof. Abhishek Sinha: Improved Guarantees for Constrained Online Convex Optimization via Self-Contraction.
May 01, 2026	I joined MBZUAI as a visiting student, hosted by Prof. Junpei Komiyama in the Department of Machine Learning.
Apr 15, 2026	Two papers accepted at ICML 2026: Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints and Improved Algorithms for Nash Welfare in Linear Bandits.
Feb 03, 2026	Three papers accepted at AISTATS 2026: Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints, Relation-Aware Slicing in Cross-Domain Alignment, and Revisiting Social Welfare in Bandits: UCB is (Nearly) All You Need.

selected publications

ICML

Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints

Dhruv Sarkar, and Abhishek Sinha

In The 43rd International Conference on Machine Learning. Preliminary version appeared at the AAAI 2026 MATH4AI Workshop. , 2026

arXiv Bib PDF

@inproceedings{sarkar2026anytime,
  title = {Optimal Anytime Algorithms for Online Convex Optimization with Adversarial Constraints},
  author = {Sarkar, Dhruv and Sinha, Abhishek},
  booktitle = {The 43rd International Conference on Machine Learning},
  year = {2026},
}

ICML

Improved Algorithms for Nash Welfare in Linear Bandits

Dhruv Sarkar, Nishant Pandey, and Sayak Ray Chowdhury

In The 43rd International Conference on Machine Learning, 2026

arXiv Bib PDF

@inproceedings{sarkar2026nashlinear,
  title = {Improved Algorithms for Nash Welfare in Linear Bandits},
  author = {Sarkar, Dhruv and Pandey, Nishant and Ray Chowdhury, Sayak},
  booktitle = {The 43rd International Conference on Machine Learning},
  year = {2026},
}

AISTATS

Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints

Dhruv Sarkar, Aprameyo Chakrabartty, Subhamon Supantha, Palash Dey, and Abhishek Sinha

In The 29th International Conference on Artificial Intelligence and Statistics, 2026

arXiv Bib HTML PDF

@inproceedings{sarkar2026projectionfree,
  title = {Projection-free Algorithms for Online Convex Optimization with Adversarial Constraints},
  author = {Sarkar, Dhruv and Chakrabartty, Aprameyo and Supantha, Subhamon and Dey, Palash and Sinha, Abhishek},
  booktitle = {The 29th International Conference on Artificial Intelligence and Statistics},
  year = {2026},
}

AAAI

DP-NCB: Privacy Preserving Fair Bandits

Dhruv Sarkar, Nishant Pandey, and Sayak Ray Chowdhury

In The 40th AAAI Conference on Artificial Intelligence, 2026

DOI arXiv Bib PDF

@inproceedings{sarkar2026dpncb,
  title = {DP-NCB: Privacy Preserving Fair Bandits},
  author = {Sarkar, Dhruv and Pandey, Nishant and Ray Chowdhury, Sayak},
  booktitle = {The 40th AAAI Conference on Artificial Intelligence},
  year = {2026},
  doi = {10.1609/aaai.v40i30.39710},
}