Fitness and Overfitness: Implicit Regularization in Evolutionary Dynamics

A common assumption in evolutionary thought is that adaptation drives an increase in biological complexity. However, the rules governing evolution of complexity appear more nuanced. Evolution is deeply connected to learning, where complexity is much better understood, with established results on optimal complexity appropriate for a given learning task. In this work, we suggest a mathematical framework for studying the relationship between evolved organismal complexity and enviroenmntal complexity by leveraging a mathematical isomorphism between evolutionary dynamics and learning theory. Namely, between the replicator equation and sequential Bayesian learning, with evolving types corresponding to competing hypotheses and fitness in a given environment to likelihood of observed evidence. In Bayesian learning, implicit regularization prevents overfitting and drives the inference of hypotheses whose complexity matches the learning challenge. We show how these results naturally carry over to the evolutionary setting, where they are interpreted as organism complexity evolving to match the complexity of the environment, with too complex or too simple organisms suffering from \textit{overfitness} and \textit{underfitness}, respectively. Other aspects, peculiar to evolution and not to learning, reveal additional trends. One such trend is that frequently changing environments decrease selected complexity, a result with potential implications to both evolution and learning. Together, our results suggest that the balance between over-adaptation to transient environmental features, and insufficient flexiblity in responding to environmental challenges, drives the emergence of optimal complexity, reflecting environmental structure. This framework offers new ways of thinking about biological complexity, suggesting new potential causes for it to increase or decrease in different environments.