StatsMLlib: A Lean 4 Library Formally Verifying Probability, Statistics, and ML Theorems

ChengleiSi · x · 2026-08-03

StatsMLlib is a formal mathematics library in Lean 4, aiming to provide a unified foundation for probability, statistics, and machine learning. It covers concentration inequalities, metric entropy and chaining, empirical processes, Rademacher complexity, random matrix theory, and finite-sample learning guarantees, with every proof checked by the Lean 4 kernel. The library currently includes 666 theorems, 1,219 lemmas, 352 definitions, 89 Lean files, and 64,695 lines of Lean code, with zero sorries. Organized by Fanghui Liu and Jason D. Lee, contributions are welcome.

Original post →

More from Research

Research channel →