The topology of statistical verifiability

zbMATH Open1483.62209arXiv1707.09378MaRDI QIDQ3384072FDOQ3384072

Authors: Konstantin Genin, Kevin T. Kelly Error creating thumbnail:

Publication date: 14 December 2021

Abstract: Topological models of empirical and formal inquiry are increasingly prevalent. They have emerged in such diverse fields as domain theory [1, 16], formal learning theory [18], epistemology and philosophy of science [10, 15, 8, 9, 2], statistics [6, 7] and modal logic [17, 4]. In those applications, open sets are typically interpreted as hypotheses deductively verifiable by true propositional information that rules out relevant possibilities. However, in statistical data analysis, one routinely receives random samples logically compatible with every statistical hypothesis. We bridge the gap between propositional and statistical data by solving for the unique topology on probability measures in which the open sets are exactly the statistically verifiable hypotheses. Furthermore, we extend that result to a topological characterization of learnability in the limit from statistical data.

Full work available at URL: https://arxiv.org/abs/1707.09378

Recommendations

• A topological criterion for hypothesis testing
• Topological properties of concept spaces (full version)
• Data features1
• scientific article; zbMATH DE number 3303999
• Topological Properties of Concept Spaces

Mathematics Subject Classification ID

Asymptotic properties of nonparametric inference (62G20) Statistical aspects of big data and data science (62R07) Topological data analysis (62R40)

Cites Work

• Title not available (Why is that?)
• A topological criterion for hypothesis testing
• Topological properties of concept spaces (full version)
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the solvability of inductive problems: a study in epistemic topology
• A general classification rule for probability measures
• Hypothesis testing for families of ergodic processes
• On a class of time inhomogeneous nonsingular flows and Schrödinger operators
• Subset space public announcement logic
• \(\Sigma^{0}_\alpha\)-admissible representations. (Extended abstract)
• On the relation between realizable and nonrealizable cases of the sequence prediction problem
• Topological subset space models for public announcements

Cited In (1)

• Causal learning with Occam's razor

This page was built for publication: The topology of statistical verifiability

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3384072)