{"work":{"id":"666d4dea-669b-423b-9bd4-e14eee78fcb4","openalex_id":null,"doi":null,"arxiv_id":"2305.01582","raw_key":null,"title":"Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl","authors":null,"authors_text":"Miles Cranmer (Princeton University, Flatiron Institute)","year":2023,"venue":"astro-ph.IM","abstract":"PySR is an open-source library for practical symbolic regression, a type of machine learning which aims to discover human-interpretable symbolic models. PySR was developed to democratize and popularize symbolic regression for the sciences, and is built on a high-performance distributed back-end, a flexible search algorithm, and interfaces with several deep learning packages. PySR's internal search algorithm is a multi-population evolutionary algorithm, which consists of a unique evolve-simplify-optimize loop, designed for optimization of unknown scalar constants in newly-discovered empirical expressions. PySR's backend is the extremely optimized Julia library SymbolicRegression.jl, which can be used directly from Julia. It is capable of fusing user-defined operators into SIMD kernels at runtime, performing automatic differentiation, and distributing populations of expressions to thousands of cores across a cluster. In describing this software, we also introduce a new benchmark, \"EmpiricalBench,\" to quantify the applicability of symbolic regression algorithms in science. This benchmark measures recovery of historical empirical equations from original and synthetic datasets.","external_url":"https://arxiv.org/abs/2305.01582","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-17T01:48:50.415018+00:00","pith_arxiv_id":"2305.01582","created_at":"2026-05-09T06:25:48.439680+00:00","updated_at":"2026-05-17T01:48:50.415018+00:00","title_quality_ok":true,"display_title":"Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl","render_title":"Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl"},"hub":{"state":{"work_id":"666d4dea-669b-423b-9bd4-e14eee78fcb4","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":34,"external_cited_by_count":null,"distinct_field_count":12,"first_pith_cited_at":"2024-04-30T17:58:29+00:00","last_pith_cited_at":"2026-05-14T17:59:55+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-17T04:19:20.548874+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"method","n":4},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":4},{"context_polarity":"use_method","n":4},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}