AI4SLT: Empirical Processes in Lean 4 for Formal Statistical Learning Theory
Yuanhe Zhang, Jason Lee, Fanghui Liu
Abstract
We present the first comprehensive Lean 4 formalization of statistical learning theory (SLT) grounded in empirical process theory. Our end-to-end formal infrastructure implement the missing contents in latest Lean library, including a complete development of Gaussian Lipschitz concentration, Dudley’s entropy integral theorem for sub-Gaussian processes, and an application to least-squares (sparse) regression with a sharp rate. The project was carried out using a human-AI collaborative workflow, in which humans design proof strategies and AI agents execute tactical proof construction, leading to the human-verified Lean 4 toolbox for SLT. Beyond implementation, the formalization process exposes and resolves implicit assumptions and missing details in standard SLT textbooks, enforcing a granular, line-by-line understanding of the theory. This work establishes a reusable formal foundation and opens the door for future developments in machine learning theory. The code is provided in https://github.com/YuanheZ/lean-stat-learning-theory.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on3
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- Intermediate Layer Optimization for Inverse Problems using Deep Generative ModelsGiannis Daras, Joseph Dean, Ajil Jalal, Alex DimakisICML 2021 · 101 citations
- Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer NetworksAndrea Montanari, Pierfrancesco UrbaniNeurIPS 2025 · 29 citations
Related papers
- FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning TheoryXiao-Wen Yang, Zihao Zhang, Jianuo Cao, Zhi Zhou et al.ICLR 2026 · 8 citations
- ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint EmbeddingsPrithwish Jana, Kaan Kale, Ahmet Ege Tanriverdi, Cruise Song et al.ICLR 2026 · 19 citations
- Lean Finder: Semantic Search for Mathlib That Understands User IntentsJialin Lu, Kye Emond, Kaiyu Yang, Swarat Chaudhuri et al.ICLR 2026 · 10 citations
- Lean-Auto: An Interface Between Lean 4 and Automated Theorem ProversYicheng Qian, Joshua Clune, Clark W. Barrett, Jeremy AvigadCAV 2025 · 6 citations
- LeanAgent: Lifelong Learning for Formal Theorem ProvingAdarsh Kumarappan, Mo Tiwari, Peiyang Song, Robert Joseph George et al.ICLR 2025
