Welcome!
I am a 4th year Ph.D. student in the Statistics Department at the University of Michigan advised by Ambuj Tewari. Previously, I studied Computer Science and Chemical Engineering also at UM where I worked with Mahdi Cheraghchi, Sindhu Kutty, and Andrej Lenert. Last summer (2024), I interned at Apple with Kunal Talwar and Hilal Asi, where I worked on online learning and differential privacy. Currently, I’m back interning at Apple working on the theory and practice of generative machine learning with Kunal Talwar, Hilal Asi, and Satyen Kale. This coming summer (2025), I will be interning at Google Research with Matthew Joseph!
My research interests broadly lie in statistical learning theory and algorithm design. Some specific areas of interest include: online learning, bandits, differential privacy, adversarial robustness, and algorithms with predictions. Nowadays, I am interested in the theory and practice of generative machine learning, especially problems around efficient alignment and reasoning.
I am grateful to be supported by the National Science Foundation Graduate Research Fellowship (NSF GRFP) and the 2025 Apple Scholars in AI/ML PhD Fellowship.
Click here for my (probably approximately) recent CV.
Working Preprints
Some work on generation and alignment coming soon :)
In Submission
- Tracking the Best Expert Privately
with Hilal Asi and Aadirupa Saha
In Submission, 2025. - Representative Language Generation
with Charlotte Peale and Omer Reingold
In Submission, 2025. - Generation through the lens of learning theory
with Jiaxun Li and Ambuj Tewari
In Submission, 2025. - Generation from Noisy Examples
with Ananth Raman
In Submission, 2025. - Faster Rates for Private Adversarial Bandits
with Hilal Asi, Kunal Talwar
In Submission, 2025
Publications
The Complexity of Sequential Prediction in Dynamical Systems
with Unique Subedi, Ambuj Tewari
Oral at Conference on Learning for Dynamics and Control (L4DC), 2025A Unified Theory of Supervised Online Learnability
with Unique Subedi, Ambuj Tewari
Outstanding Paper Award at Conference on Algorithmic Learning Theory (ALT), 2025A Characterization of Multioutput Learnability
with Unique Subedi, Ambuj Tewari
Journal of Machine Learning Research (JMLR), 2024Online Classification with Predictions
with Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2024Smoothed Online Classification can be Harder than Batch Classification
with Unique Subedi, Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2024Multiclass Transductive Online Learning
with Steve Hanneke, Amirreza Shaeiri, Unique Subedi
Spotlight at Conference on Neural Information Processing Systems (NeurIPS), 2024Apple Tasting: Combinatorial Dimensions and Minimax Rates
with Ananth Raman , Unique Subedi, Ambuj Tewari
Conference on Learning Theory (COLT), 2024Online Learning with Set-Valued Feedback
with Unique Subedi, Ambuj Tewari
Conference on Learning Theory (COLT), 2024Online Infinite-Dimensional Regression: Learning Linear Operators
with Unique Subedi, Ambuj Tewari
Conference on Algorithmic Learning Theory (ALT), 2024Multiclass Online Learnability under Bandit Feedback
with Ananth Raman , Unique Subedi, Idan Mehalel, Ambuj Tewari
Conference on Algorithmic Learning Theory (ALT), 2024On the Learnability of Multilabel Ranking
with Unique Subedi, Ambuj Tewari
Spotlight at Conference on Neural Information Processing Systems (NeurIPS), 2023On Proper Learnability between Average- and Worst-case Robustness
with Unique Subedi, Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2023Multiclass Online Learning and Uniform Convergence
with Steve Hanneke, Shay Moran, Unique Subedi, Ambuj Tewari
Conference on Learning Theory (COLT), 2023Online Agnostic Multiclass Boosting
with Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2022Design of thermophotovoltaics for tolerance of parasitic absorption
with Tobias Burger, Andrej Lenert
Optics Express, 2019
Projects
I have also been working on more empirical research, especially towards understanding the abilities and limitations of the Transformer architecture. Below are some ongoing projects which highlight some of my findings.
Talks
- A Unified Theory of Supervised Online Learnability (ALT 2025)
- Generation through the lens of learning theory (Apple 2025)
- Generation through the lens of learning theory (NEU CS Theory Seminar) [slides]
- Generation through the lens of learning theory (STATS 700 Guest Lecture)
- Trichotomies in Online Learnability (Student ML Research Seminar 2024) [slides]
- Trichotomies in Online Learnability (Apple 2024) [slides]
- Revisiting the Learnability of Apple Tasting (MSSISS 2024)
- Multiclass Online Learnability under Bandit Feedback (ALT 2024)
- Multiclass Online Learning and Uniform Convergence (UM EECS Theory Seminar) [slides]
- On Classification-Calibration of Gamma-Phi Losses (COLT 2023) [slides]
Awards and Fellowships
- Apple Scholars in AI/ML PhD Fellowship (2025)
- ALT Outstanding Paper Award (2025)
- MSSISS Best Oral Presentation (2024)
- NeurIPS Scholar Award (2022, 2023)
- Outstanding First-year Ph.D. Student (2022)
- NSF Graduate Research Fellowship (2022)
- First-year Rackham Fellowship (2021)
Teaching
I really enjoy teaching. Here are a couple courses and organizations that I have taught for in the past:
- PhD Math Preparation Workshop, Fall 2023
- STATS 507 (Data Science using Python), Fall 2022, Winter 2023
- STATS 315 (Introduction to Deep Learning), Winter 2022
- STATS 250 (Introduction to Statistics), Fall 2021
- InspiritAI, Summer 2021
- AI4ALL, Summer 2021
- ChE 330 (Chemical and Engineering Thermodynamics), Winter 2018
Hobbies
Apart from research, I am a big fan of bodybuilding and actively keep up with the Mr. Olympia.