Information Efficiency of Scientific Automation

TL;DR

This paper models scientific discovery as a thermodynamic process, deriving bounds on information gain under finite work budgets and proposing an efficiency metric to compare learning strategies in scientific automation.

Contribution

It introduces a thermodynamic framework for understanding scientific automation, deriving bounds on information gain and proposing an efficiency metric for different learning strategies.

Findings

Finite-work bounds on information gain in Bayesian learning.

Federated learning can be more efficient than unpartitioned strategies.

Guidance on optimizing scientific automation efforts.

Abstract

Scientific discovery can be framed as a thermodynamic process in which an agent invests physical work to acquire information about an environment under a finite work budget. Using established results about the thermodynamics of computing, we derive finite-budget bounds on information gain over rounds of sequential Bayesian learning. We also propose a metric of information-work efficiency, and compare unpartitioned and federated learning strategies under matched work budgets. The presented results offer guidance in the form of bounds and an information efficiency metric for efforts in scientific automation at large.