Chinmaya Kausik
Mathematics Ph.D. Student, University of Michigan.
![prof_pic.jpg](/assets/img/prof_pic.jpg?25b0f9727cdab3b0f973ebf5c5821d93)
Hi there! I’m Chinmaya Kausik, a 3rd year mathematics Ph.D. candidate at UMich working on sequential decision making, statistics, optimization and machine learning. I am being co-advised by Prof. Ambuj Tewari and Prof. Martin Strauss.
Check out my papers, projects, and personal interests!
What do I care about, academically?
- Tackling tangible, real-world questions with a principled mathematical approach. These days, my work focuses on sequential decision making under various settings - offline-to-online transfer, partial observability/latent information and non-standard feedback and reward models. I also have side projects in deep learning. On the other hand, a lot of my undergraduate background was in geometry, topology and dynamics, with work in computer-assisted topology and geometry.
- Increasing accessibility to and in higher mathematics and creating communities where ideas cross pollinate and people pull each other up. I have started the Stats, Physics, Astronomy, Math (SPAM) graduate student social initiative at the University of Michigan. I also co-founded and co-organize Monsoon Math Camp. I have also been involved in building and expanding other mathematical communities, like platforms for the PolyMath REU, DRP programs and the undergraduate math organization at IISc, etc.
What am I doing these days?
- Interning at Microsoft in the advertiser optimization team under Ajith Moparthi, working on bidding algorithms and value maximization!
- Collaborating with Yonathan Efroni (Meta), Aadirupa Saha (Apple), Nadav Merlis (ENSEA) on algorithms for bandit and reinforcement learning algorithms with feedback at varying costs and accuracies, also called multi-fidelity feedback.
- Thinking about principled approaches to data collection and learning for RLHF under real-world considerations.
- Formulating problems in learning under latent information and nonstationarity in bandits.
- Organizing an interdepartmental social initiative, SPAM (Statistics, Physics, Astronomy, Mathematics).
- Fleshing out ideas for more academic communities like Monsoon Math.
What do I want to learn about/do in the future?
primary goals
- Complete an empirical study of RLHF methods on LLMs of varying size and understand the implementation nuances of major RLHF methods.
- Work on a large scale applied recommender systems project using the latent bandit algorithms that I designed (LOCAL-UCB and ProBALL-UCB).
- Applying ideas from RLHF and bandits to mental health studies that my advisor is involved in.
side-quests
- Design a codenames bot using one LLM and train it againts players designed using a different LLM.
- Explore the nuances of implementing various RL algorithms in simulated motion settings.
- Design meaningful experiments to compare LLM agents trained using language feedback with RL agents trained using numerical feedback, using benchmark frameworks like LLF-bench.
news
Nov 29, 2023 | I have received the Rackham International Student Fellowship, which is offered to 25 students across graduate departments under Rackham! |
---|---|
Oct 29, 2023 | Our paper “Denoising Low-Rank Data Under Distribution Shift: Double Descent and Data Augmentation” has been accepted to the NeurIPS workshop on the Mathematics of Modern Machine Learning (M3L)! |
Jun 15, 2023 | Two new preprints (confounded RL and double descent phenomena with input noise) added to arXiv! |
Apr 29, 2023 | My paper on learning mixtures of Markov chains and MDPs with Kevin Tan and my advisor, Prof. Tewari, has been accepted to ICML 2023 (Oral)! |
Apr 07, 2023 | Invited to attend the Princeton ML theory Summer School, 2023! |