About Me
I am a third year Ph.D. student in Statistics at the University of Michigan advised by Ambuj Tewari. Prior to attending the University of Michigan, I earned my Bachelor’s degree in Computer Science and Applied Statistics from Purdue University, where I worked with Denny Yu on building machine learning models for healthcare ergonomics application. During my undergraduate studies, I was a research fellow at the University of California, Berkeley, where I worked with Jiantao Jiao on continual learning algorithms.
My research interests lie in developing AI safety methods for pre-trained machine learning models. I have worked on developing rejectors that identify uncertain parts of a sequence prediction, enabling experts to fill in the gaps. Additionally, I have explored robust decision-making using uncertain machine learning predictions. I am currently working on applying these methods to tackle challenges in protein design to improve the reliability of these predictions.
In Submission
Learning to Partially Defer for Sequences
Sahana Rayan, Ambuj Tewari
In Submission, 2025Conformal Robust Control of Linear Systems
Yash Patel, Sahana Rayan, Ambuj Tewari
In Submission, 2025
Publications
- Conformal Contextual Robust Optimization
Yash Patel, Sahana Rayan, Ambuj Tewari
International Conference on Artificial Intelligence and Statistics, 2024
Talks
- Learning to Partially Defer for Sequences
2025 Michigan Student Symposium for Interdisciplinary Statistical Sciences
Awards
- PhD Student Service Award, 2024
- Outstanding Graduate Student Instructor Team Award Honorable Mention, 2023
Teaching
- Bayesian Data Analysis (DATASCI 451) - Winter 2025
- Statistics and Artificial Intelligence (DATASCI 315) - Winter 2023, Fall 2023, Winter 2024, Fall 2024
- Introduction to Statistics and Data Analysis (STATS 250) - Fall 2022