Timezone: »

 
Poster
Neural Symbolic Regression that scales
Luca Biggio · Tommaso Bendinelli · Alexander Neitz · Aurelien Lucchi · Giambattista Parascandolo

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @
in Poster Session 1 »

Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditionally, symbolic regression methods use hand-designed strategies that do not improve with experience. In this paper, we introduce the first symbolic regression method that leverages large scale pre-training. We procedurally generate an unbounded set of equations, and simultaneously pre-train a Transformer to predict the symbolic equation from a corresponding set of input-output-pairs. At test time, we query the model on a new set of points and use its output to guide the search for the equation. We show empirically that this approach can re-discover a set of well-known physical equations, and that it improves over time with more data and compute.

Keywords: Deep Learning

Author Information

Luca Biggio (ETH Zürich)
Tommaso Bendinelli (CSEM)
Alexander Neitz (Max Planck Institute for Intelligent Systems)
Aurelien Lucchi (ETH Zurich)
Giambattista Parascandolo (Max Planck Institute for Intelligent Systems and ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors