Decoupling Representation and Learning in Genetic Programming: the LaSER Approach

TL;DR

LaSER introduces a framework that separates representation evolution from learning in genetic programming, enabling more flexible models and better generalization by integrating external learners like neural networks.

Contribution

It presents LaSER, a novel approach that decouples representation evolution from lifetime learning, allowing the use of diverse function approximators in genetic programming.

Findings

LaSER outperforms standard GP and linear regression on complex datasets.

Enables emergence of innate representations supporting evolutionary hypotheses.

Supports flexible modeling beyond symbolic forms.

Abstract

Genetic Programming (GP) has traditionally entangled the evolution of symbolic representations with their performance-based evaluation, often relying solely on raw fitness scores. This tight coupling makes GP solutions more fragile and prone to overfitting, reducing their ability to generalize. In this work, we propose LaSER (Latent Semantic Representation Regression)} -- a general framework that decouples representation evolution from lifetime learning. At each generation, candidate programs produce features which are passed to an external learner to model the target task. This approach enables any function approximator, from linear models to neural networks, to serve as a lifetime learner, allowing expressive modeling beyond conventional symbolic forms. Here we show for the first time that LaSER can outcompete standard GP and GP followed by linear regression when it employs non-linear methods to fit coefficients to GP-generated equations against complex data sets. Further, we explore how LaSER enables the emergence of innate representations, supporting long-standing hypotheses in evolutionary learning such as the Baldwin Effect. By separating the roles of representation and adaptation, LaSER offers a principled and extensible framework for symbolic regression and classification.