Learning to generalize in evolution through annealed population heterogeneity

TL;DR

This paper shows that annealed population heterogeneity, where individuals experience different environments over time, acts as an implicit regularizer, promoting evolutionary strategies that generalize across changing conditions.

Contribution

It introduces annealed heterogeneity as a novel mechanism for evolutionary generalization, linking it to stochastic gradient descent concepts and demonstrating its effects through simulations and theory.

Findings

Annealed heterogeneity biases evolution toward generalist solutions.

It introduces a variance-weighted demographic noise term.

The process is analogous to mini-batching in stochastic gradient descent.

Abstract

Evolutionary systems must learn to generalize, often extrapolating from a limited set of selective conditions to anticipate future environmental changes. The mechanisms enabling such generalization remain poorly understood, despite their importance to predict ecological robustness, drug resistance, or design future-proof vaccination strategies. Here, we demonstrate that annealed population heterogeneity, wherein distinct individuals in the population experience different instances of a complex environment over time, can act as a form of implicit regularization and facilitate evolutionary generalization. Mathematically, annealed heterogeneity introduces a variance-weighted demographic noise term that penalizes across-environment fitness variance and effectively rescales the population size, thereby biasing evolution toward generalist solutions. This process is indeed analogous to a variant of the mini-batching strategy employed in stochastic gradient descent, where an effective multiplicative noise produces an inductive bias by triggering noise-induced transitions. Through numerical simulations and theoretical analysis we discuss the conditions under which variation in how individuals experience environmental selection can naturally promote evolutionary strategies that generalize across environments and anticipate novel challenges.