4 papers
ERBench: A Benchmark and Testsuite for Equation Discovery Algorithms
Paul Kahlmeyer, Henrik Voigt, Michael Habeck +1
Equation discovery aims to automate the discovery of scientific models in the form of mathematical equations from data. Technically, equation discovery is implemented by symbolic r…
Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis
Henrik Voigt, Michael Habeck, Joachim Giesen
Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque tra…
Analyzing Generalization in Pre-Trained Symbolic Regression
Henrik Voigt, Paul Kahlmeyer, Kai Lawonn +2
Symbolic regression algorithms search a space of mathematical expressions for formulas that explain given data. Transformer-based models have emerged as a promising, scalable appro…
Scaling Up Unbiased Search-based Symbolic Regression
Paul Kahlmeyer, Joachim Giesen, Michael Habeck +1
In a regression task, a function is learned from labeled data to predict the labels at new data points. The goal is to achieve small prediction errors. In symbolic regression, the…