Research

My main research focus is in the mathematical foundations of data science, particularly the algorithmic primitives that drive modern data science and machine learning tasks. This involves statistics, high-dimensional probability, algorithms, optimization and sampling, and some algebra. Recently I’ve been interested in more applied statistics, particularly Bayesian methods, the PCS (Predictability-Computability-Stability) framework, and causal inference.

Publications

You can also find my articles on my Google Scholar profile.

Preprints

Polytope Sampling at the Speed of Isoperimetry
Anming Gu, BS, Kevin Tian, Hubert Yang
[arXiv]

Perspectives on Stochastic Localization
BS, Kevin Tian, Matthew S. Zhang
[arXiv]

Journal Papers

Efficient Tensor Decomposition via Moment Matrix Extension
BS, Julia Lindberg, Joe Kileel
In Journal of Symbolic Computation
[journal] [arXiv] [code]

Concentration Inequalities for Sums of Markov Dependent Random Matrices
Joe Neeman, BS, Rachel Ward
In Information and Inference
[journal] [arXiv]

Generalization Bounds for Sparse Random Feature Expansions
Abolfazl Hashemi, Hayden Schaeffer, BS, Ufuk Topcu, Giang Tran, Rachel Ward
In Applied and Computational Harmonic Analysis
[journal] [arXiv] [code]

Conference Papers

Functional Stochastic Localization
Anming Gu, BS, Kevin Tian
In Conference on Learning Theory 2026
[conference] [arXiv]

SHRIMP: Sparser Random Feature Models via Iterative Magnitude Pruning
Yuege Xie, BS, Hayden Schaeffer, Rachel Ward
In Mathematical and Scientific Machine Learning 2022
[conference] [arXiv] [code]