At MIT, my current research focuses on statistical inference, theoretical machine learning, and information theory. A topic that I have been studying is called empirical Bayes.
List of my publications:- [Arxiv] Jana, S., Polyanskiy, Y., Teh, A., Wu, Y. Empirical Bayes via ERM and Rademacher complexities: the Poisson model. Conference on Learning Theory (COLT), 2023.
- [Arxiv] Teh, A., Polyanskiy, Y. Comparing Poisson and Gaussian Channels. IEEE International Symposium on Information Theory (ISIT), 2023.
- [Link] Xu, X., Leonardi, C., Teh, A., Jao, D., Wang, K., Yu, W., Azarderakhsh, R. Improved Digital Signatures Based on Elliptic Curve Endomorphism Rings, International Conference on Information Security Practice and Experience (ISPEC), 2019, pp. 293-309, doi:10.1007/978-3-030-34339-2_16.
- Feature Alignment via Energy Distance (MIT SDS Conference 2024).
- Comparing Poisson and Gaussian Channels (ISIT 2023, 2023 North American School of Information Theory).
- Empirical Bayes Method for Short-Term Time Series Forecasting (MIT SDS Conference 2022, Princeton Theoretical Machine Learning Summer School (Student Poster session)).
My undergraduate research experience include:
- Internship at Uber ATG (2019).
- Cryptography research (2018).
- Graph theory research (2017).