Solves the structural redundancy problem in symbolic regression by collapsing expression DAG isomorphisms.
March 24, 2026
Original Paper
Instruction Set and Language for Symbolic Regression
arXiv · 2603.21836
The Takeaway
Symbolic regression is often inefficient because the search space is cluttered with mathematically identical representations. IsalSR provides a canonical language that eliminates these redundancies, significantly speeding up the search for governing equations in scientific discovery.
From the abstract
A fundamental but largely unaddressed obstacle in Symbolic regression (SR) is structural redundancy: every expression DAG with admits many distinct node-numbering schemes that all encode the same expression, each occupying a separate point in the search space and consuming fitness evaluations without adding diversity. We present IsalSR (Instruction Set and Language for Symbolic Regression), a representation framework that encodes expression DAGs as strings over a compact two-tier alphabet and co