Exploring Unknown Universes in Probabilistic Relational Models

• URL: http://arxiv.org/abs/2001.02021v1
• Date: Tue, 7 Jan 2020 13:26:55 GMT
• Title: Exploring Unknown Universes in Probabilistic Relational Models
• Authors: Tanya Braun, Ralf M\"oller
• Abstract summary: Large probabilistic models are often shaped by a pool of known individuals (a universe) and relations between them. The aim of this paper is to define a semantics for models with unknown universes decoupled from a specific constraint language to enable lifted and thereby, tractable inference.
• Score: 4.438240667468304
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large probabilistic models are often shaped by a pool of known individuals (a universe) and relations between them. Lifted inference algorithms handle sets of known individuals for tractable inference. Universes may not always be known, though, or may only described by assumptions such as "small universes are more likely". Without a universe, inference is no longer possible for lifted algorithms, losing their advantage of tractable inference. The aim of this paper is to define a semantics for models with unknown universes decoupled from a specific constraint language to enable lifted and thereby, tractable inference.

Related papers

• Deep Learning is Not So Mysterious or Different [54.5330466151362]
  We argue that anomalous generalization behaviour is not distinct to neural networks. We present soft inductive biases as a key unifying principle in explaining these phenomena. We also highlight how deep learning is relatively distinct in other ways, such as its ability for representation learning.
  arXiv  Detail & Related papers  (2025-03-03T22:56:04Z)
• Quantum collapse as undecidable proposition in an Everettian multiverse [0.0]
  Our representation of the Universe is built with sequences of symbols, numbers, operators, rules and undecidable propositions defining our mathematical truths. Each representation is at all effects a physical subset of the Universe, a metastructure of events in space and time, which actively participate to the evolution of the Universe as we are internal observers.
  arXiv  Detail & Related papers  (2024-01-24T10:01:14Z)
• A single space-time is too small for all of Wigner's friends [0.0]
  Recent no-go theorems on interpretations of quantum theory are shown to have an unexpectedly strong corollary. One cannot reject AOE and at the same time assume that the observed events' in question can all be embedded within a single background space-time common to all observers.
  arXiv  Detail & Related papers  (2023-12-19T00:03:58Z)
• A Measure-Theoretic Axiomatisation of Causality [55.6970314129444]
  We argue in favour of taking Kolmogorov's measure-theoretic axiomatisation of probability as the starting point towards an axiomatisation of causality. Our proposed framework is rigorously grounded in measure theory, but it also sheds light on long-standing limitations of existing frameworks.
  arXiv  Detail & Related papers  (2023-05-19T13:15:48Z)
• Unextendibility, uncompletability, and many-copy indistinguishable ensembles [77.34726150561087]
  We study unextendibility, uncompletability and analyze their connections to many-copy indistinguishable ensembles. We report a class of multipartite many-copy indistinguishable ensembles for which local indistinguishability property increases with decreasing mixedness.
  arXiv  Detail & Related papers  (2023-03-30T16:16:41Z)
• $\omega$PAP Spaces: Reasoning Denotationally About Higher-Order, Recursive Probabilistic and Differentiable Programs [64.25762042361839]
  $omega$PAP spaces are spaces for reasoning denotationally about expressive differentiable and probabilistic programming languages. Our semantics is general enough to assign meanings to most practical probabilistic and differentiable programs. We establish the almost-everywhere differentiability of probabilistic programs' trace density functions.
  arXiv  Detail & Related papers  (2023-02-21T12:50:05Z)
• Does the Universe have its own mass? [62.997667081978825]
  The mass of the universe is a distribution of non-zero values of gravitational constraints. A formulation of the Euclidean quantum theory of gravity is also proposed to determine the initial state. Being unrelated to ordinary matter, the distribution of its own mass affects the geometry of space.
  arXiv  Detail & Related papers  (2022-12-23T22:01:32Z)
• Aspects of Superdeterminism Made Intuitive [0.0]
  We show that superdeterministic correlations may exist as a matter of principle, but be undetectable for all practical purposes. We also show that probability theory, as a physical theory, indicates that superdeterminism has a greater explanatory power than its competitors.
  arXiv  Detail & Related papers  (2022-05-21T14:59:06Z)
• Life in a random universe: Sciama's argument reconsidered [5.15018725021934]
  We show that a random universe can masquerade as intelligently designed,' with the fundamental constants instead appearing to be fined to achieve the highest probability for life to occur. For our universe, this mechanism may only require there to be around a dozen currently unknown fundamental constants.
  arXiv  Detail & Related papers  (2021-09-10T23:15:31Z)
• A Short Note on the Relationship of Information Gain and Eluder Dimension [86.86653394312134]
  We show that eluder dimension and information gain are equivalent in a precise sense for reproducing kernel Hilbert spaces. We show that this is not a coincidence -- eluder dimension and information gain are equivalent in a precise sense for reproducing kernel Hilbert spaces.
  arXiv  Detail & Related papers  (2021-07-06T04:01:22Z)
• Generalized Probabilistic Theories in a New Light [0.0]
  A new answer to the question of why our universe is quantum mechanical rather than classical will be presented. This paper shows that there is still a possibility that there might be a deterministic level from which our universe emerges.
  arXiv  Detail & Related papers  (2021-03-08T21:28:19Z)
• The principle of majorization: application to random quantum circuits [68.8204255655161]
  Three classes of circuits were considered: (i) universal, (ii) classically simulatable, and (iii) neither universal nor classically simulatable. We verified that all the families of circuits satisfy on average the principle of majorization. Clear differences appear in the fluctuations of the Lorenz curves associated to states.
  arXiv  Detail & Related papers  (2021-02-19T16:07:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.