Graduate Student, Princeton University
ab7728[at]princeton[dot]edu
anandbrahmbhatt27[at]gmail[dot]com
anand[dot]brahmbhatt[at]iitdalumni[dot]com

Research Interests
Online Non-Stochastic Control
Learning Theory

Bio

I am a graduate student in the Computer Science Department at Princeton University, where I work with Prof. Elad Hazan. I was generously awarded the prestegious Gordon Y.S. Wu Fellowship for incoming graduate students at Princeton University. My current research focuses on efficient online non-stochastic control, where I aim to develop new techniques for controlling dynamical systems and explore their implications for sequence-to-sequence models. I am particularly motivated by developing abstract, mathematical perspectives on learning algorithms and uncovering their connections to deeper structures in mathematics.

Previously, I was a Pre-Doctoral Researcher at Google Research India, working in the Advertising Sciences team under the mentorship of Dr. Rishi Saket and Dr. Aravindan Raghuveer. My work focused on understanding the learnability of aggregate data and the privacy guarantees afforded by such aggregations.

I also interned at Adobe Research, Bengaluru, where I collaborated with Dr. Shiv Kumar Saini and Dr. Atanu R Sinha on designing fairer methods for cloud resource allocation.

I graduated from the Indian Institute of Technology, Delhi in 2022. My undergraduate thesis, supervised by Prof. Parag Singla and Prof. Mausam, focused on identifying causes of and mitigating bias amplification in deep networks. I was also mentored by Prof. Amitabha Tripathi during a summer project on graph labelings.

IIT Delhi
June 2018 - May 2022
Adobe Research
May 2021 - August 2021
Google Research
July 2022 - July 2024
Princeton University
August 2024 - present

Updates

  • [April 2025] Our paper A New Approach to Controlling Linear Dynamical Systems is now available on arXiv.
  • [March 2025] Our paper Measures for Closeness to Cordiality for Graphs got published in the Discrete Applied Mathematics journal.
  • [October 2024] Attended CIKM 2024 in Boise to present our paper LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions.
  • [August 2024] Joined Princeton University as a graduate student under the guidance of Prof. Elad Hazan.
  • [July 2024] Our paper LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions got accepted to CIKM 2024.
  • [December 2023] Attended NeurIPS 2023 in New Orleans to present our paper PAC Learning Linear Thresholds from Label Proportions.
  • [September 2023] Our paper PAC Learning Linear Thresholds from Label Proportions was accepted to NeurIPS 2023 as a Spotlight.
  • [August 2023] US Patent approved for our work on Cloud-Based Resource Allocation using Meters at Adobe Research.
  • [July 2023] Attended the Conference on Learning Theory (COLT) 2023 in Bengaluru.
  • [July 2022] Joined Google Research India as a Pre-Doctoral Researcher in the Ad Sciences Team.
  • [May 2022] Graduated with a Bachelor’s in Computer Science and Engineering from IIT Delhi.
  • [May 2021] Joined Adobe Research, Bengaluru as a Research Intern.

Publications & Patents

A New Approach to Controlling Linear Dynamical Systems

Anand Brahmbhatt#, Gon Buzaglo#, Sofiia Druchyna# ,Elad Hazan# (#-alphabetical)
Preprint Paper

PAC Learning Linear Thresholds from Label Proportions

Anand Brahmbhatt*, Rishi Saket*, Aravindan Raghuveer (*-equal contribution)
Spotlight Paper @ NeurIPS 2023 Conference Paper

LLP-Bench: A Large Scale Tabular Benchmark for Learning from Label Proportions

Anand Brahmbhatt*, Mohith Pokala*, Rishi Saket, Aravindan Raghuveer (*-equal controbution)
CIKM, 2024 Conference Paper

Measures for Closeness to Cordiality for Graphs

Anand Brahmbhatt#, Kartikeya Rai#, Amitabha Tripathi# (#-alphabetical)
Discrete Applied Mathematics, 2025 Journal Paper

Cloud Based Resource Allocation Using Meters

Atanu R Sinha, Shiv Kumar Saini, Sapthotharan Nair, Saarthak Marathe, Manupriya Gupta, Anand Brahmbhatt, Ayush Chauhan
US Patent 20230259403 Patent

Label Differential Privacy via Aggregation

Anand Brahmbhatt, Rishi Saket, Shreyas Havaldar, Anshul Nasery, Aravindan Raghuveer
Preprint Paper

Towards Fair and Calibrated Models

Anand Brahmbhatt, Vipul Rathore, Mausam, Parag Singla
Preprint Paper