I am a third-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.

Working Preprints

The author list is alphabetical unless otherwise stated. (*) indicates equal contribution.

Under Review

The author list is alphabetical unless otherwise stated. (*) indicates equal contribution.

• The Complexity of Sequential Prediction in Dynamical Systems
  Vinod Raman*, Unique Subedi*, Ananth Raman, Ambuj Tewari
  Submitted, 2024

• Apple Tasting: Combinatorial Dimensions and Minimax Rates
  Vinod Raman*, Unique Subedi*, Ananth Raman, Ambuj Tewari
  Submitted, 2023

• A Combinatorial Characterization of Supervised Online Learnability
  Vinod Raman*, Unique Subedi*, Ambuj Tewari
  Submitted, 2023

• Online Learning with Set-Valued Feedback
  Vinod Raman*, Unique Subedi* , Ambuj Tewari
  Submitted, 2023

• A Characterization of Multioutput Learnability
  Vinod Raman*, Unique Subedi*, Ambuj Tewari
  Submitted, 2023

Publications

The author list is alphabetical unless otherwise stated. (*) indicates equal contribution.

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

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

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

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

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

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

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

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

• A Weighted Version of Erdős-Kac Theorem
  Undergraduate Thesis

Talks

• A Weighted Version of Erdos-Kac Theorem (Number Theory Seminar, Ole Miss)
• Computational Investigations of Random Multiplicative Functions (FUSRP 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