Research map / Probabilistic and scientific modeling / Molecules and proteins
Differentiable Genetic Programming for High-dimensional Symbolic Regression
Xiaotian Song, Peng Zeng, Andrew Lensen, Hengzhe Zhang, Yuwei Ou, Yanan Sun, Mengjie Zhang, Jiancheng Lv
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace evolutionary-only search with gradient-based structure optimization (DGP vs GP) | GP · DLBCL | test R2: 0.06 -> 0.32 | Improved |
| replace evolutionary-only search with gradient-based structure optimization (DGP vs GP) | GP · Fri_c4_100 | test R2: 0.32 -> 0.58 | Improved |
| use DGP instead of GP | GP · Tecator | test R2: 0.87 -> 0.88 | No clear effect |
| use DGP instead of MGPRC | MGPRC · Satellite_image | test R2: 0.61 -> 0.63 | No clear effect |
| use DGP instead of DSR on DLBCL | DSR · DLBCL | test R2: -349.84 -> 0.32 | Improved |
| use DGP instead of PSSR on DLBCL | PSSR · DLBCL | test R2: -58.68 -> 0.32 | Improved |
| use DGP instead of GP for recovery | GP · Synthetic S1-S6 | recovery rate: 13.3 -> 73.3 | Improved |
| use DGP instead of PSSR for recovery | PSSR · Synthetic S1-S6 | recovery rate: 68.3 -> 73.3 | Improved |
| use DGP instead of GP for program size | GP · Satellite_image | program size (nodes): 136 -> 61 | Improved |
| use DGP instead of NSGP for program size | NSGP · Fri_c0_50 | program size (nodes): 86 -> 26 | Improved |
| use DGP instead of DSR for program size | DSR · Satellite_image | program size (nodes): 10 -> 61 | Hurt |
Closest papers by meaning
- Racing Control Variable Genetic Programming for Symbolic Regression (AAAI 2024 · similarity 0.86)
- Improving Monte Carlo Tree Search for Symbolic Regression (NeurIPS 2025 · similarity 0.86)
- An Interpretable Approach to the Solutions of High-Dimensional Partial Differential Equations (AAAI 2024 · similarity 0.86)
- A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data (ICML 2024 · similarity 0.85)
- Symbolic Regression with a Learned Concept Library (NeurIPS 2024 · similarity 0.85)
- FunctionEvolve: Structure-Guided Symbolic Regression with LLMs (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
