# Maximum-entropy from the probability calculus: exchangeability, sufficiency

## TL;DR

This paper explores how maximum-entropy distributions naturally emerge as approximations in probability calculus through exchangeability and sufficiency models, favoring exchangeability, and discusses their implications and validity.

## Contribution

It demonstrates that maximum-entropy distributions can be derived as approximations from exchangeability or sufficiency models, highlighting the preference for exchangeability.

## Key findings

- Maximum-entropy arises as an approximation in probability calculus.
- Exchangeability models are preferable over sufficiency models.
- The paper discusses the validity and implications of maximum-entropy approximations.

## Abstract

Maximum-entropy distributions are shown to appear in the probability calculus as approximations of a model by exchangeability or a model by sufficiency, the former model being preferable. The implications of this fact are discussed, together with other questions: Prediction or retrodiction? How good is the maximum-entropy approximation? Is this a "derivation" of maximum-entropy?