Research map / Probabilistic and scientific modeling / Molecules and proteins
Neural Symbolic Regression that scales
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Increase pre-training data from 10K to 10M equation skeletons | NeSymReS · Five test datasets | accuracy | Helped |
| Use pre-training on procedurally generated equations | NeSymReS · Five test datasets | accuracy and test-time efficiency | Helped |
| Increase the number of input-output pairs available at test time | NeSymReS · Five test datasets | accuracy | Helped |
| Use NeSymReS rather than Genetic Programming | Symbolic regression on AI-Feynman · AI-Feynman | time to reach maximum accuracy: more than three orders of magnitudes faster | Helped |
| Use Gaussian Process regression rather than symbolic regression | Gaussian Processes · In-distribution versus out-of-distribution evaluation | accuracy | Mixed |
| Use NeSymReS with a prior favoring equations containing constants on equations without constants | NeSymReS · SOOSE-NC | accuracy | Hurt |
| Use NeSymReS rather than other tested baselines | Symbolic regression · Nguyen | accuracy | Helped |
| Increase test-time compute | NeSymReS · Five test datasets | accuracy | Helped |
Closest papers by meaning
- Deep Generative Symbolic Regression (ICLR 2023 · similarity 0.92)
- Online Symbolic Regression with Informative Query (AAAI 2023 · similarity 0.90)
- Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length (ICLR 2025 · similarity 0.88)
- A Neural-Guided Dynamic Symbolic Network for Exploring Mathematical Expressions from Data (ICML 2024 · similarity 0.88)
- SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training (ICLR 2024 · similarity 0.88)
- ParFam -- (Neural Guided) Symbolic Regression via Continuous Global Optimization (ICLR 2025 · similarity 0.86)
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.