The principle of maximum entropy and a problem in probability kinematics

Lukits, Stefan

doi:10.1007/s11229-013-0335-8

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Associated with the Log score via McCarthy's theorem (Theorem 2.2) is the Kullback-Leibler divergence, which is the most promising concept of difference for probability distributions in information theory and the one which gives us Bayesian standard conditioning as well as Jeffrey conditioning (see Lukits, 2013). It is noncommutative and may provide the kind of asymmetry required to reflect epistemic asymmetry.…”

Section: Expectations For Information Theorymentioning

confidence: 99%

Symmetry and partial belief geometry

Lukits

2021

Euro Jnl Phil Sci

Self Cite

View full text Add to dashboard Cite

When beliefs are quantified as credences, they are related to each other in terms of closeness and accuracy. The "accuracy first" approach in formal epistemology wants to establish a normative account for credences (probabilism, Bayesian conditioning, principle of indifference, and so on) based entirely on the alethic properties of the credence: how close it is to the truth. To pull off this project, there is a need for a scoring rule. There is widespread agreement about some constraints on this scoring rule (for example propriety), but not whether a unique scoring rule stands above the rest. The Brier score equips credences with a structure similar to metric space and induces a "geometry of reason." It enjoys great popularity in the current debate. I point out many of its weaknesses in this article. An alternative approach is to reject the geometry of reason and accept information theory in its stead. Information theory comes fully equipped with an axiomatic approach which covers probabilism, standard conditioning, and Jeffrey conditioning. It is not based on an underlying topology of a metric space, but uses a non-commutative divergence instead of a symmetric distance measure. I show that information theory, despite initial promise, also fails to accommodate basic epistemic intuitions; and speculate on its remediation.

show abstract

Section: Expectations For Information Theorymentioning

confidence: 99%

Symmetry and partial belief geometry

Lukits

2021

Euro Jnl Phil Sci

Self Cite

View full text Add to dashboard Cite

show abstract

Epistemic justification: its subjective and its objective ways

Spohn

2017

Synthese

View full text Add to dashboard Cite

Objective standards for justification or for being a reason would be desirable, but inductive skepticism tells us that they cannot be presupposed. Rather, we have to start from subjective-relative notions of justification and of being a reason. The paper lays out the strategic options we have given this dilemma. The paper explains the requirements for this subject-relative notion and how they may be satisfied. Then it discusses four quite heterogeneous ways of providing more objective standards, which combine without guaranteeing complete success.

show abstract

Rules of proof for maximal entropy inference

Landes

2023

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

The principle of maximum entropy and a problem in probability kinematics

Cited by 5 publications

References 12 publications

Symmetry and partial belief geometry

Symmetry and partial belief geometry

Epistemic justification: its subjective and its objective ways

Rules of proof for maximal entropy inference

Contact Info

Product

Resources

About