Reversing information flow: retrodiction in semicartesian categories

• URL: http://arxiv.org/abs/2401.17447v1
• Date: Tue, 30 Jan 2024 21:20:26 GMT
• Title: Reversing information flow: retrodiction in semicartesian categories
• Authors: Arthur J. Parzygnat
• Abstract summary: In statistical inference, retrodiction is the act of inferring potential causes in the past based on knowledge of the effects in the present and the dynamics leading to the present. Recently, an axiomatic definition of retrodiction has been made in a way that is applicable to both classical and quantum probability. Almost simultaneously, a framework for information flow in in terms of semicartesian categories has been proposed.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In statistical inference, retrodiction is the act of inferring potential causes in the past based on knowledge of the effects in the present and the dynamics leading to the present. Retrodiction is applicable even when the dynamics is not reversible, and it agrees with the reverse dynamics when it exists, so that retrodiction may be viewed as an extension of inversion, i.e., time-reversal. Recently, an axiomatic definition of retrodiction has been made in a way that is applicable to both classical and quantum probability using ideas from category theory. Almost simultaneously, a framework for information flow in in terms of semicartesian categories has been proposed in the setting of categorical probability theory. Here, we formulate a general definition of retrodiction to add to the information flow axioms in semicartesian categories, thus providing an abstract framework for retrodiction beyond classical and quantum probability theory. More precisely, we extend Bayesian inference, and more generally Jeffrey's probability kinematics, to arbitrary semicartesian categories.

Related papers

• Considering a superposition of classical reference frames [0.0]
  We consider a framework in which classical reference frames may be in superposition relative to one another. A rule for transforming wavefunctions from one system to another system in superposition is proposed and consistency with the Schrodinger equation is demonstrated.
  arXiv  Detail & Related papers  (2023-12-21T02:46:45Z)
• Deep Backtracking Counterfactuals for Causally Compliant Explanations [57.94160431716524]
  We introduce a practical method called deep backtracking counterfactuals (DeepBC) for computing backtracking counterfactuals in structural causal models. As a special case, our formulation reduces to methods in the field of counterfactual explanations.
  arXiv  Detail & Related papers  (2023-10-11T17:11:10Z)
• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Bayesian Renormalization [68.8204255655161]
  We present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference. The main insight of Bayesian Renormalization is that the Fisher metric defines a correlation length that plays the role of an emergent RG scale. We provide insight into how the Bayesian Renormalization scheme relates to existing methods for data compression and data generation.
  arXiv  Detail & Related papers  (2023-05-17T18:00:28Z)
• Axioms for retrodiction: achieving time-reversal symmetry with a prior [2.28438857884398]
  We propose a category-theoretic definition of retrodiction and use it to exhibit a time-reversal symmetry for all quantum channels. Retrodiction functors exhibit an inferential time-reversal symmetry consistent with the standard formulation of quantum theory.
  arXiv  Detail & Related papers  (2022-10-24T18:33:24Z)
• Log-linear Guardedness and its Implications [116.87322784046926]
  Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. This work formally defines the notion of log-linear guardedness as the inability of an adversary to predict the concept directly from the representation. We show that, in the binary case, under certain assumptions, a downstream log-linear model cannot recover the erased concept.
  arXiv  Detail & Related papers  (2022-10-18T17:30:02Z)
• Bayesian Recurrent Units and the Forward-Backward Algorithm [91.39701446828144]
  Using Bayes's theorem, we derive a unit-wise recurrence as well as a backward recursion similar to the forward-backward algorithm. The resulting Bayesian recurrent units can be integrated as recurrent neural networks within deep learning frameworks. Experiments on speech recognition indicate that adding the derived units at the end of state-of-the-art recurrent architectures can improve the performance at a very low cost in terms of trainable parameters.
  arXiv  Detail & Related papers  (2022-07-21T14:00:52Z)
• Quantum retrodiction: foundations and controversies [0.0]
  Retrodiction is the making of statements about past events based on current information. We present the foundations of quantum retrodiction and highlight its intimate connection with the Bayesian interpretation of probability.
  arXiv  Detail & Related papers  (2021-03-10T14:20:47Z)
• Causal Expectation-Maximisation [70.45873402967297]
  We show that causal inference is NP-hard even in models characterised by polytree-shaped graphs. We introduce the causal EM algorithm to reconstruct the uncertainty about the latent variables from data about categorical manifest variables. We argue that there appears to be an unnoticed limitation to the trending idea that counterfactual bounds can often be computed without knowledge of the structural equations.
  arXiv  Detail & Related papers  (2020-11-04T10:25:13Z)
• Fluctuation theorems from Bayesian retrodiction [2.28438857884398]
  We show that the reverse channel very naturally arises from Bayesian retrodiction, both in classical and quantum theories. More generally, with the reverse process constructed on consistent logical inference, fluctuation relations acquire a much broader form and scope.
  arXiv  Detail & Related papers  (2020-09-07T01:42:05Z)
• Inverses, disintegrations, and Bayesian inversion in quantum Markov categories [0.0]
  We introduce quantum Markov categories as a structure that refines and extends a synthetic approach to probability theory and information theory. We analyze three successively more general notions of reversibility and statistical inference.
  arXiv  Detail & Related papers  (2020-01-21T11:19:04Z)

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.