dorsal/arxiv
View SchemaUpdating Probabilities
| Authors | Ariel Caticha, Adom Giffin |
|---|---|
| Categories | |
| ArXiv ID | physics/0608185 |
| URL | https://arxiv.org/abs/physics/0608185 |
| DOI | 10.1063/1.2423258 |
Abstract
We show that Skilling's method of induction leads to a unique general theory of inductive inference, the method of Maximum relative Entropy (ME). The main tool for updating probabilities is the logarithmic relative entropy; other entropies such as those of Renyi or Tsallis are ruled out. We also show that Bayes updating is a special case of ME updating and thus, that the two are completely compatible.
{
"annotation_id": "04a2a84e-efc4-43e2-a786-e50e82f2943f",
"date_created": "2026-03-02T18:01:11.501000Z",
"date_modified": "2026-03-02T18:01:11.501000Z",
"file_hash": "3c03f056a17428a65155abd9eb0521ee63101f56efdc33449efb319bcff6cd8f",
"private": false,
"record": {
"abstract": "We show that Skilling\u0027s method of induction leads to a unique general theory\nof inductive inference, the method of Maximum relative Entropy (ME). The main\ntool for updating probabilities is the logarithmic relative entropy; other\nentropies such as those of Renyi or Tsallis are ruled out. We also show that\nBayes updating is a special case of ME updating and thus, that the two are\ncompletely compatible.",
"arxiv_id": "physics/0608185",
"authors": [
"Ariel Caticha",
"Adom Giffin"
],
"categories": [
"physics.data-an",
"cond-mat.stat-mech",
"cs.IT",
"math.IT"
],
"doi": "10.1063/1.2423258",
"title": "Updating Probabilities",
"url": "https://arxiv.org/abs/physics/0608185"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "828de39a-9c20-48c8-856a-b681dd663f9d",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}