About Me
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. My topics of interest include learning theory, online learning, adversarial robustness, vector-valued prediction, operator learning, and partial-feedback models, dynamical systems. In the past, I have also worked on probabilistic number theory.
Preprints
On the Benefits of Active Data Collection in Operator Learning
with Ambuj Tewari
Preprint, 2024Error Bounds for Learning Fourier Linear Operators
with Ambuj Tewari
Preprint, 2024The Complexity of Sequential Prediction in Dynamical Systems
with Vinod Raman, Ambuj Tewari
Preprint, 2024A Combinatorial Characterization of Supervised Online Learnability
with Vinod Raman, Ambuj Tewari
Preprint, 2023
Publications
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 Spotlight atConference on Neural Information Processing Systems (NeurIPS), 2024
Smoothed Online Classification can be Harder than Batch Classification
with Vinod Raman, Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2024Online Learning with Set-Valued Feedback
with Vinod Raman, Ambuj Tewari
Conference on Learning Theory (COLT), 2024Apple Tasting: Combinatorial Dimensions and Minimax Rates
with Vinod Raman, Ananth Raman, Ambuj Tewari
Conference on Learning Theory (COLT), 2024Online Infinite-Dimensional Regression: Learning Linear Operators
with Vinod Raman, Ambuj Tewari
Conference on Algorithmic Learning Theory (ALT), 2024Multiclass Online Learnability under Bandit Feedback
with Ananth Raman, Vinod Raman, Idan Mehalel, Ambuj Tewari
Conference on Algorithmic Learning Theory (ALT), 2024On the Learnability of Multilabel Ranking
with Vinod Raman, Ambuj Tewari
Spotlight at Conference on Neural Information Processing Systems (NeurIPS), 2023On Proper Learnability between Average- and Worst-case Robustness
with Vinod Raman, Ambuj Tewari
Conference on Neural Information Processing Systems (NeurIPS), 2023Multiclass Online Learning and Uniform Convergence
with Steve Hanneke, Shay Moran, Vinod Raman, Ambuj Tewari
Conference on Learning Theory (COLT), 2023A Weighted Version of Erdős-Kac Theorem
with Rizwanur Khan, Micah Milinovich
Journal of Number Theory, 2022A Conjectural Asymptotic Formula for Multiplicative Chaos in Number Theory
with Daksh Aggarwal, William Verreault, Asif Zaman, Chengui Zheng
Research in Number Theory, 2022Sums 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
- 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)