Pith. sign in

REVIEW

Maximizing the information learned from finite data selects a simple model

Not yet reviewed by Pith; the record is open.

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 1705.01166 v3 pith:KPHNJMAD submitted 2017-05-02 physics.data-an cond-mat.stat-mechcs.ITmath.ITmath.STstat.MLstat.TH

classification physics.data-ancond-mat.stat-mechcs.ITmath.ITmath.STstat.MLstat.TH
keywords datapriorparameterparameterseffectiveinformationlimitselects
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We use the language of uninformative Bayesian prior choice to study the selection of appropriately simple effective models. We advocate for the prior which maximizes the mutual information between parameters and predictions, learning as much as possible from limited data. When many parameters are poorly constrained by the available data, we find that this prior puts weight only on boundaries of the parameter manifold. Thus it selects a lower-dimensional effective theory in a principled way, ignoring irrelevant parameter directions. In the limit where there is sufficient data to tightly constrain any number of parameters, this reduces to Jeffreys prior. But we argue that this limit is pathological when applied to the hyper-ribbon parameter manifolds generic in science, because it leads to dramatic dependence on effects invisible to experiment.

Discussion (0). Continue with ORCID to comment.

Pith tools