[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"VNGRFkEChD":3},"\n\u003Cdiv align=\"center\">\n\n# Lean Machine Learning\n\n## The Lean library for machine learning research.\n\n\u003C/div>\n\n\nWebsite: [https://leanmachinelearning.github.io/](https://leanmachinelearning.github.io/)\n\n## Goals\n\n- A library of high-quality formalization of machine learning definitions.\n- Essential theorems and proofs in machine learning theory.\n- A framework for working on machine learning algorithms in Lean.\n- An extensive documentation, with examples and tutorials.\n- A trusted basis for formalization of machine learning research.\n\n## Contributing\n\nPlease see our [contribution guide](CONTRIBUTING.md) and [code of conduct](CODE_OF_CONDUCT.md).\n\nFor discussions, you can reach out to us on the [Lean prover Zulip chat](https://leanprover.zulipchat.com/).\n\nYou can also see the [roadmap](https://leanmachinelearning.github.io/roadmap) for ideas on what to work on.\n\n## Current state of the library\n\nAs a first proof of concept, the repository contains a formalization of regret bounds for several stochastic bandit algorithms.\n\nMain results:\n- Framework for working on (bandit) algorithms in Lean.\n- Regret bound for the Explore-Then-Commit algorithm.\n- Regret bound for the UCB algorithm.\n",1776560102576]