Year: 2024
Type: preprint
Abstract: Efficiently harvesting thermodynamic resources requires a precise understanding of their structure. This becomes explicit through the lens of information engines -- thermodynamic engines that use information as fuel. Maximizing the work harvested using available information is a form of physically-instantiated machine learning that drives information engines to develop complex predictive memory to store an environment's temporal correlations. We show that an information engine's complex predictive memory poses both energetic benefits and risks. While increasing memory facilitates detection of hidden patterns in an environment, it also opens the possibility of thermodynamic overfitting, where the engine dissipates additional energy in testing. To address overfitting, we introduce thermodynamic regularizers that incur a cost to engine complexity in training due to the physical constraints on the information engine. We demonstrate that regularized thermodynamic machine learning generalizes effectively. In particular, the physical constraints from which regularizers are derived improve the performance of learned predictive models. This suggests that the laws of physics jointly create the conditions for emergent complexity and predictive intelligence.
Source: arXiv (Cornell University)
Institutions: University of California, Davis, Trinity College Dublin
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
Funders: Silicon Valley Community Foundation, John Templeton Foundation, Fetzer Institute, Foundational Questions Institute, National Research Foundation, Agency for Science, Technology and Research, National Research Foundation Singapore, Irish Research Council, Templeton World Charity Foundation, Army Research Office, Army Research Laboratory
OpenAlex ID: W4392270652