Instability and Information

Abstract

Many complex systems exhibit extreme events far more often than expected for a normal distribution. This work examines how self-similar bursts of activity across several orders of magnitude can emerge from first principles in systems that adapt to information. Surprising connections are found between two apparently unrelated research topics: hand-eye coordination in balancing tasks and speculative trading in financial markets. Seemingly paradoxically, locally minimising fluctuations can increase a dynamical system's sensitivity to unpredictable perturbations and thereby facilitate global catastrophes. This general principle is studied in several domain-specific models and in behavioural experiments. It explains many findings in both fields and resolves an apparent antinomy: the coexistence of stabilising control or market efficiency and perpetual instabilities resembling critical phenomena in physical systems.