Back to search

Cornell University

A UNIFIED THEORY OF PROBABILISTIC MODELING, DEPENDENCE, AND INCONSISTENCY

Abstract

dc:description.abstract

What should you do with conflicting information? To be rational, you must immediately resolve the inconsistency, so as to maintain a consistent (probabilistic) picture of the world. But how? And is it really critical to do so immediately Inconsistency is clearly undesirable, but we stand to gain a lot by representing it. This thesis develops a broad theory of how to approach probabilistic modeling with possibly-inconsistent information, unifying and reframing much of the literature in the process. The key ingredient is a novel kind of graphical model, called a Probabilistic Dependency Graph (PDG), which allows for arbitrary (even conflicting) pieces of probabilistic information. In Part I, we establish PDGs as a generalization of other models of mental state, including traditional graphical models such as Bayesian Networks and Factor Graphs, as well as causal models, and even generalizations of probability distributions, such as Dempster-Shafer Belief functions. In Part II, we show that PDGs also capture modern neural representations. Surprisingly, standard loss functions can be viewed as the inconsistency of a PDG that models the situation appropriately.Furthermore, many important algorithms in AI are instances of a simple approach to resolving inconsistencies. In Part III, we provide algorithms for PDG inference, and uncover a deep algorithmic equivalence between the problems of inference and calculating a PDG’s numerical degree of inconsistency. We also develop powerful yet inutuitive principles for reasoning with (and about) PDGs.

Degree

thesis:*
Name thesis:degree_name
Ph. D., Computer Science
Level thesis:degree_level
Doctor of Philosophy
Discipline thesis:degree_discipline
Computer Science
Grantor
Cornell University
Year dc:date.issued
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Richardson, Oliver
Chair dc:contributor.chair
  • Halpern, Joseph
Committee members dc:contributor.committeemember
  • Kozen, Dexter
  • Goldfeld, Ziv
  • De Sa, Christopher

Subjects

dc:subject × 6

Rights

dc:rights
Statement dc:rights
  • Attribution-ShareAlike 4.0 International
Language dc:language.iso
en

Identifiers

dc:identifier.*
Dc Identifier Bibid
16922010
Dc Identifier Other
ProQuest Submission ID: 14646
ProQuest Publication ID: 31556739

Chain of custody

source
Harvested from
Cornell University
Base URL
ecommons.cornell.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Richardson, Oliver. A UNIFIED THEORY OF PROBABILISTIC MODELING, DEPENDENCE, AND INCONSISTENCY. Doctor of Philosophy thesis, Cornell University, 2024. https://hdl.handle.net/1813/117234