Palestrante: Etienne Russeil, Université Clermont-Auvergne (France)

Local: Auditório da FEN

Data: 05.12.2023 - Horário 16h

A palestra será em inglês

Title: Multiview Symbolic Regression: How to learn laws from examples

Abstract: Symbolic Regression is a data-driven method that searches the space of mathematical equations to find the best analytical representation of a given dataset. It is a very powerful tool, which enables the emergence of underlying behavior governing the data generation process. Furthermore, in the case of scientific equations, obtaining an analytical form adds a layer of interpretability to the answer, which might highlight interesting properties. However, equations built with traditional Symbolic Regression approaches are limited to describing one particular event at a time. That is, if a given parametric equation were at the origin of two datasets produced using two sets of parameters, the method would output two particular solutions with specific parameter values for each event, instead of finding a common parametric equation. In this work, we propose an adaptation of Symbolic Regression that is capable of recovering a common parametric equation hidden behind multiple datasets generated using different parameter values. We call this approach Multiview Symbolic Regression (MvSR) and propose an implementation inside the operon framework. We demonstrate how it can recover expressions from incomplete pieces of information carried by multiple examples. We further highlight the potential of MvSR by demonstrating its efficiency on a variety of real scientific datasets. The resulting parametric equations can correctly describe the examples from which they were built as well as other unseen similar examples