Dr Kevin Han Huang
Website:
Email: kevin[dot]huang[at]warwick.ac.uk
Office: MB3.13
I am a postdoctoral research fellow funded by the EPSRC , working with Gareth Roberts at Warwick statistics and at . I received my PhD in machine learning from the , where I was advised by at Gatsby and at . I was a visiting researcher at the advised by during Spring 2024, where I worked on AI-for-physics algorithms. Prior to my PhD, I received my Bachelor and Master in mathematics from .
For the academic year 25-26, I am co-organising the . I am also organising the ProbAI Theory of Scaling Laws WorkshopLink opens in a new window at Warwick in summer 2026.
I am a machine learning (ML) theorist, with increasingly frequent excursions to the applied side of things. On the theory end, I study the emergence of universal structures in large-scale stochastic systems. I develop and apply tools from:
- Probability theory, e.g. universality and random matrix theory;
- High-dimensional statistics, especially for non-linear estimators and dependent data;
- Symmetry-based inference;
- Stochastic optimisation and sampling theory.
On the empirical side of things, I am excited about problems that involve scaling and statistical diagnostics of ML models. Some examples include:
- Scaling laws of neural networks;
- Algorithm design for AI for materials science;
- Robustness and safety of AI models.