Vinod Raman

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. This past summer (2024), I interned at Apple with Kunal Talwar and Hilal Asi, where I worked on online learning and differential privacy!

My research interests broadly lie in statistical learning theory and algorithm design. Some specific areas of interest include: online learning theory, bandits, differential privacy, adversarial robustness, and algorithms with predictions. Currently, I am interested in bridging learning theory and generative machine learning with applications to Transformers and Large Language Models (LLMs). I am also working on empirical research aimed at understanding the abilities and limitations of Transformers and other modern sequence-to-sequence models.

Publications

Generation from Noisy Examples

Ananth Raman, Vinod Raman

Multiclass Transductive Online Learning

Steve Hanneke, Vinod Raman, Amirreza Shaeiri, Unique Subedi

arXiv.org 2024

Generation through the lens of learning theory

Vinod Raman, Ambuj Tewari

arXiv.org 2024

Smoothed Online Classification can be Harder than Batch Classification

Vinod Raman, Unique Subedi, Ambuj Tewari

arXiv.org 2024

Online Classification with Predictions

Vinod Raman, Ambuj Tewari

arXiv.org 2024

The Complexity of Sequential Prediction in Dynamical Systems

Vinod Raman, Unique Subedi, Ambuj Tewari

arXiv.org 2024

Apple Tasting: Combinatorial Dimensions and Minimax Rates

Apple Tasting: Combinatorial Dimensions and Minimax Rates

Vinod Raman, Unique Subedi, Ananth Raman, Ambuj Tewari

Annual Conference Computational Learning Theory 2023

Online Infinite-Dimensional Regression: Learning Linear Operators

Vinod Raman, Unique Subedi, Ambuj Tewari

International Conference on Algorithmic Learning Theory 2023

Multiclass Online Learnability under Bandit Feedback

Multiclass Online Learnability under Bandit Feedback

A. Raman, Vinod Raman, Unique Subedi, Ambuj Tewari

International Conference on Algorithmic Learning Theory 2023

A Combinatorial Characterization of Supervised Online Learnability

Vinod Raman, Unique Subedi, Ambuj Tewari

Online Learning with Set-Valued Feedback

Online Learning with Set-Valued Feedback

Vinod Raman, Unique Subedi, Ambuj Tewari

Annual Conference Computational Learning Theory 2023

On the Learnability of Multilabel Ranking

On the Learnability of Multilabel Ranking

Vinod Raman, Unique Subedi, Ambuj Tewari

Neural Information Processing Systems 2023

Multiclass Online Learning and Uniform Convergence

Steve Hanneke, S. Moran, Vinod Raman, Unique Subedi, Ambuj Tewari

Annual Conference Computational Learning Theory 2023

A Characterization of Multioutput Learnability

Vinod Raman, Unique Subedi, Ambuj Tewari

On Proper Learnability between Average- and Worst-case Robustness

On Proper Learnability between Average- and Worst-case Robustness

Vinod Raman, Unique Subedi, Ambuj Tewari

Neural Information Processing Systems 2022

Online Agnostic Multiclass Boosting

Online Agnostic Multiclass Boosting

Vinod Raman, Ambuj Tewari

Neural Information Processing Systems 2022

Design of thermophotovoltaics for tolerance of parasitic absorption.

Vinod Raman, T. Burger, A. Lenert

Optics Express 2019

A Characterization of Multilabel Learnability

Vinod Raman, Unique Subedi, Ambuj Tewari

arXiv.org 2023

A Characterization of Online Multiclass Learnability

Vinod Raman, Unique Subedi, Ambuj Tewari

arXiv.org 2023

Probabilistically Robust PAC Learning

Probabilistically Robust PAC Learning

Vinod Raman, Unique Subedi, Ambuj Tewari

arXiv.org 2022