Globally Optimal Symbolic Regression

10/29/2017

∙

In this study we introduce a new technique for symbolic regression that guarantees global optimality. This is achieved by formulating a mixed integer non-linear program (MINLP) whose solution is a symbolic mathematical expression of minimum complexity that explains the observations. We demonstrate our approach by rediscovering Kepler's law on planetary motion using exoplanet data and Galileo's pendulum periodicity equation using experimental data.

READ FULL TEXT

Globally Optimal Symbolic Regression

Learning Symbolic Expressions: Mixed-Integer Formulations, Cuts, and Heuristics

Symbolic Regression using Mixed-Integer Nonlinear Optimization

Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: A systematic scientific machine learning approach

Maximum a-Posteriori Estimation for the Gaussian Mixture Model via Mixed Integer Nonlinear Programming

Controllable Neural Symbolic Regression

A distribution-free mixed-integer optimization approach to hierarchical modelling of clustered and longitudinal data

Automatic generation of interpretable hyperelastic material models by symbolic regression

Globally Optimal Symbolic Regression

Related Research

Learning Symbolic Expressions: Mixed-Integer Formulations, Cuts, and Heuristics

Symbolic Regression using Mixed-Integer Nonlinear Optimization

Efficient hybrid modeling and sorption model discovery for non-linear advection-diffusion-sorption systems: A systematic scientific machine learning approach

Maximum a-Posteriori Estimation for the Gaussian Mixture Model via Mixed Integer Nonlinear Programming

Controllable Neural Symbolic Regression

A distribution-free mixed-integer optimization approach to hierarchical modelling of clustered and longitudinal data

Automatic generation of interpretable hyperelastic material models by symbolic regression