Exponential-family distributions are the beating heart of many modern AI/ML systems, including that of the poor AI agent that coded this website. My research here deals with fundamental problems in learning these distributions in parametric settings. When possible, we try to prove non-asymptotic sample complexity results and try to keep our computational complexities polynomial. From a physics perspective, all of these works are very closely related to inverse problems in statistical physics. Below you will find results about learning Ising models, Potts models, Phi-4 theories, and even systems with Grassmann variables.
Learning theory for exponential families
Provable, sample-efficient recovery of high-dimensional distributions.
Papers
- Learning of discrete graphical models with neural networksAdvances in Neural Information Processing Systems, 2020
- Discrete distributions are learnable from metastable samplesNature Communications, 2026
- Finite Sample Bounds for Learning with Score MatchingIn The Thirty Ninth Annual Conference on Learning Theory , 2026
- Efficient learning of lattice gauge theories with fermionsPhys. Rev. D, Jun 2026