TherML: Thermodynamics of Machine Learning

Alexander A. Alemi; Ian Fischer

TherML: Thermodynamics of Machine Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.04162 v3 pith:3SQC33MU submitted 2018-07-11 cs.LG cond-mat.stat-mechstat.ML

Alexander A. Alemi , Ian Fischer This is my paper

classification cs.LGcond-mat.stat-mechstat.ML

keywords learningmachinethermodynamicsworkclasscorrespondencedevelopdiscuss

verification ladder T0 review T1 audit T2 compute T3 formal

0 comments

read the original abstract

In this work we offer a framework for reasoning about a wide class of existing objectives in machine learning. We develop a formal correspondence between this work and thermodynamics and discuss its implications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

SGD as Free Energy Minimization: A Thermodynamic View on Neural Network Training
cs.LG 2025-05 reject novelty 5.0 of 10

SGD is said to minimize free energy, but the temperature is constructed from the data, making the validation circular.

Pith tools