Saved in:
Bibliographic Details
Main Author: Rao, Mihir
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.15671
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912719356035072
author Rao, Mihir
author_facet Rao, Mihir
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15671
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Information Efficiency of Scientific Automation
Rao, Mihir
Information Theory
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.
title Information Efficiency of Scientific Automation
topic Information Theory
url https://arxiv.org/abs/2511.15671