Graduate Student, Massachusetts Institute of Technology
navodita[at]mit[dot]edu
navoditasharma16[at]gmail[dot]com

Bio

I am a first-year PhD student at MIT, advised by Prof. Pulkit Agrawal.

Prior to this, I was a Research Engineer at Google DeepMind, where my work spanned a variety of research areas. My latest research involved developing differentially private algorithms for offline reinforcement learning, in collaboration with Dr. Alekh Agarwal, Dr. Abhradeep Guha Thakurta and Dr. Christoph Dann. In the past, I have worked on developing solutions for learning from aggregated data to preserve data privacy, mentored by Dr. Aravindan Raghuveer, Dr. Rishi Saket and Dr. Karthikeyan Shanmugan.

My past research also includes automated discovery of interpretable policies from neuroscience data, and exploring how reinforcement learning can facilitate continual learning in LLM agents.

Before this role, I was an intern at Google Research where I worked with Dr. Aravindan Raghuveer and Prof. Balaraman Ravindran on Imitation Learning. Prior to this, I interned at Viterbi School of Engineering USC where, under the guidance of Prof. Xiang Ren, I worked on Time Series prediction using Knowledge Graphs.

I completed my Dual Degree (Bachelors + Masters) in Computer Science and Engineering from Indian Institute of Technology, Madras. My Dual Degree Thesis, under the guidance of Prof. Balaraman Ravindran, focused on Imitation Learning for multi-agent Traffic Signal Control.

Updates

  • [Sep 2025] Our paper Preserving Expert-Level Privacy in Offline Reinforcement Learning got accepted to TMLR and was awarded a J2C Certification.
  • [Aug 2025] Started my PhD at MIT, advised by Prof. Pulkit Agrawal.
  • [May 2025] Our paper Learning from Label Proportions and Covariate-shifted Instances got accepted to UAI 2025.
  • [May 2025] Our paper Discovering Symbolic Cognitive Models from Human and Animal Behavior got accepted to ICML 2025 for a spotlight poster presentation.
  • [January 2024] Our paper Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation got accepted to ICLR 2024.
  • [December 2023] Our paper Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation got accepted to Regulatable ML Workshop at NeurIPS 2023 as an Oral Presentation. I presented this work at NeurIPS 2023 in New Orleans.
  • [July 2022] Joined Google DeepMind as a Research Engineer in the AQUA Team.
  • [June 2021] Completed my Dual Degree (Bachelors + Masters) in Computer Science and Engineering from IIT Madras.
  • [April 2021] Joined Google Research India as a Research Intern in the Advertising Sciences Team.
  • [January 2021] Attended International Joint Conference on Artificial Intelligence (IJCAI), 2020 virtually. Presented my paper as a poster.
  • [April 2020] Our paper Temporal attribute prediction via joint modeling of multi-relational structure evolution got accepted to IJCAI 2020 as a poster.
  • [May 2019] Joined Viterbi School of Engineering, USC as a Research Intern. Was one of the 15 students selected from India through the IUSSTF-Viterbi program.

Publications & Preprints

Preserving Expert-Level Privacy in Offline Reinforcement Learning

Navodita Sharma, Vishnu Vinod, Abhradeep Thakurta, Alekh Agarwal, Borja Balle, Christoph Dann, Aravindan Raghuveer
TMLR 2025, Awarded J2C Certification Paper

Discovering Symbolic Cognitive Models from Human and Animal Behavior

Pablo Samuel Castro, Nenad Tomasev, Ankit Anand, Navodita Sharma, Rishika Mohanta, Aparna Dev, Kuba Perlin, Siddhant Jain, Kyle Levin, Noémi Éltető, Will Dabney, Alexander Novikov, Glenn C Turner, Maria K Eckstein, Nathaniel D Daw, Kevin J Miller, Kimberly L Stachenfeld
ICML 2025 Paper

Learning from Label Proportions and Covariate-shifted Instances

Sagalpreet Singh, Navodita Sharma, Shreyas Havaldar, Rishi Saket, Aravindan Raghuveer
UAI 2025 Paper

Automated discovery of interpretable cognitive programs underlying reward-guided behavior

PS Castro, N Tomasev, A Anand, Navodita Sharma, R Mohanta, A Dev, A Novikov, K Perlin, N Elteto, S Jain, K Levin, M Eckstein, W Dabney, GC Turner, N Daw, K Stachenfeld, KJ Miller
COSYNE 2025

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

Shreyas Havaldar*, Navodita Sharma*, Shubhi Sareen, Karthikeyan Shanmugam, Aravindan Raghuveer
ICLR 2024, Oral @ Regulatable ML Workshop, NeurIPS 2023 Paper

Temporal attribute prediction via joint modeling of multi-relational structure evolution

Sankalp Garg*, Navodita Sharma*, Woojeong Jin, Xiang Ren
IJCAI 2020 Paper