I am a fourth-year Ph.D. student in the statistics department at the University of Michigan, where I am advised by Prof. Ambuj Tewari. Previously, I studied mathematics and computer science at the University of Mississippi (Olemiss). During my time there, I was fortunate to work with Prof. Rizwanur Khan and Prof. Micah Milinovich in number theory.

Research Interest

I am broadly interested in the theory of machine learning. Some topics of interest include learning theory, online learning, adversarial robustness, vector-valued prediction, and partial-feedback models, dynamical systems. Recently, I’ve been interested in AI for Science, particularly operator learning, which aims to develop fast surrogate models for PDEs or allow black-box simulation of system behavior directly from data, even without known governing equations.

Preprints

• Operator Learning: A Statistical Perspective
  with Ambuj Tewari
  Preprint, 2025

• Controlling Statistical, Discretization, and Truncation Errors in Learning Fourier Linear Operators
  with Ambuj Tewari
  Preprint, 2024

Publications

• On the Benefits of Active Data Collection in Operator Learning
  with Ambuj Tewari
  International Conference on Machine Learning (ICML), 2025 (Spotlight)

• The Complexity of Sequential Prediction in Dynamical Systems
  with Vinod Raman, Ambuj Tewari
  Conference on Learning for Dynamics and Control (L4DC), 2025 (Oral)

• A Unified Theory of Supervised Online Learnability
  with Vinod Raman, Ambuj Tewari
  Conference on Algorithmic Learning Theory (ALT), 2025 (Outstanding Paper Award)

• A Characterization of Multioutput Learnability
  with Vinod Raman, Ambuj Tewari
  Journal of Machine Learning Research (JMLR), 2024

• Multiclass Transductive Online Learning
  with Steve Hanneke, Amirreza Shaeiri, Vinod Raman
  Conference on Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)

• Smoothed Online Classification can be Harder than Batch Classification
  with Vinod Raman, Ambuj Tewari
  Conference on Neural Information Processing Systems (NeurIPS), 2024

• Online Learning with Set-Valued Feedback
  with Vinod Raman, Ambuj Tewari
  Conference on Learning Theory (COLT), 2024

• Apple Tasting: Combinatorial Dimensions and Minimax Rates
  with Vinod Raman, Ananth Raman, Ambuj Tewari
  Conference on Learning Theory (COLT), 2024

• Online Infinite-Dimensional Regression: Learning Linear Operators
  with Vinod Raman, Ambuj Tewari
  Conference on Algorithmic Learning Theory (ALT), 2024

• Multiclass Online Learnability under Bandit Feedback
  with Ananth Raman, Vinod Raman, Idan Mehalel, Ambuj Tewari
  Conference on Algorithmic Learning Theory (ALT), 2024

• On the Learnability of Multilabel Ranking
  with Vinod Raman, Ambuj Tewari
  Conference on Neural Information Processing Systems (NeurIPS), 2023 (Spotlight)

• On Proper Learnability between Average- and Worst-case Robustness
  with Vinod Raman, Ambuj Tewari
  Conference on Neural Information Processing Systems (NeurIPS), 2023

• Multiclass Online Learning and Uniform Convergence
  with Steve Hanneke, Shay Moran, Vinod Raman, Ambuj Tewari
  Conference on Learning Theory (COLT), 2023

• A Weighted Version of Erdős-Kac Theorem
  with Rizwanur Khan, Micah Milinovich
  Journal of Number Theory, 2022

• A Conjectural Asymptotic Formula for Multiplicative Chaos in Number Theory
  with Daksh Aggarwal, William Verreault, Asif Zaman, Chengui Zheng
  Research in Number Theory, 2022

• Sums of Random Multiplicative Functions over Function Fields with Few Irreducible Factors
  with Daksh Aggarwal, William Verreault, Asif Zaman, Chengui Zheng
  Mathematical Proceedings of the Cambridge Philosophical Society, 2022

• A Weighted Version of Erdős-Kac Theorem
  Undergraduate Thesis

Talks

• On the Benefits of Active Data Collection in Operator Learning (MSSISS, 2024)
• Online Learning with Set-Valued Feedback (Signal Processing Seminar UM EECS, 2024)
• Online Infinite-Dimensional Regression: Learning Linear Operators (MSSISS, 2024)
• Online Infinite-Dimensional Regression: Learning Linear Operators (ALT 2024)
• A Weighted Version of Erdos-Kac Theorem (Number Theory Seminar, Ole Miss)
• Computational Investigations of Random Multiplicative Functions (Fields Institute, 2020)

Miscellaneous Writing

• An Elementary Evaluation of $\zeta(2n)$ Using Dirichlet’s Kernel
  Micah B. Milinovich and Unique Subedi
• On $L_1$-norm of Dirichlet’s Kernel
  Micah B. Milinovich and Unique Subedi

Teaching

I have been a Graduate Student Instructor for the following courses at Michigan:

• Probability and Distribution Theory, Fall 2023
• Statistics and AI, aka Deep Learning, Winter 2023
• Bayesian Data Analysis, Fall 2022
• Applied Regression Analysis, Winter 2022
• Introduction to Statistics and Data Analysis, (Fall 2021 & Winter 2024)