SOURCE-LINKED INTELLIGENCE

Thermodynamic Cyclic Processes with Markov Samplers in Bayesian Inference

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

The concept of Markov chain Monte Carlo (MCMC) cycles, an analogy to cyclic processes in heat engines, is presented in order to examine Bayesian inference problems. In this effort, we develop adaptive ensemble schedulers that allow the tuning of external parameters of a Bayesian canonical ensemble during an MCMC run, realising the MCMC cycles in practice. We run these cycles on different statistical models. As a fundamental insight, we find (both theoretically and in practice) that such systems can produce a non-zero net work output if and only if the considered model is non-Gaussian. As such,

Read original source ↗ Open in workspace

recordType

paper

region

Global