Picturing classical and quantum Bayesian inference
From MaRDI portal
Abstract: We introduce a graphical framework for Bayesian inference that is sufficiently general to accommodate not just the standard case but also recent proposals for a theory of quantum Bayesian inference wherein one considers density operators rather than probability distributions as representative of degrees of belief. The diagrammatic framework is stated in the graphical language of symmetric monoidal categories and of compact structures and Frobenius structures therein, in which Bayesian inversion boils down to transposition with respect to an appropriate compact structure. We characterize classical Bayesian inference in terms of a graphical property and demonstrate that our approach eliminates some purely conventional elements that appear in common representations thereof, such as whether degrees of belief are represented by probabilities or entropic quantities. We also introduce a quantum-like calculus wherein the Frobenius structure is noncommutative and show that it can accommodate Leifer's calculus of `conditional density operators'. The notion of conditional independence is also generalized to our graphical setting and we make some preliminary connections to the theory of Bayesian networks. Finally, we demonstrate how to construct a graphical Bayesian calculus within any dagger compact category.
Recommendations
Cites work
- scientific article; zbMATH DE number 2125662 (Why is no real title available?)
- scientific article; zbMATH DE number 5151673 (Why is no real title available?)
- scientific article; zbMATH DE number 4060777 (Why is no real title available?)
- scientific article; zbMATH DE number 2049998 (Why is no real title available?)
- scientific article; zbMATH DE number 1493045 (Why is no real title available?)
- scientific article; zbMATH DE number 1542063 (Why is no real title available?)
- scientific article; zbMATH DE number 3384257 (Why is no real title available?)
- A new description of orthogonal bases
- Bases in diagrammatic quantum protocols
- Cartesian bicategories. I
- Categorical formulation of finite-dimensional \(C^*\)-algebras
- Categorical semantics of linear logic
- Categories for the Practising Physicist
- Classical and quantum structuralism
- Coherence for compact closed categories
- Dagger compact closed categories and completely positive maps (extended abstract)
- Finite Dimensional Vector Spaces Are Complete for Traced Symmetric Monoidal Categories
- Finite dimensional Hilbert spaces are complete for dagger compact closed categories (extended abstract)
- Frobenius algebras and ambidextrous adjunctions
- From quantum interference to Bayesian coherence and back round again
- Graphical reasoning in compact closed categories for quantum computation
- Higher-dimensional algebra and topological quantum field theory
- POVMs and Naimark's theorem without sums
- Probability, Frequency and Reasonable Expectation
- Quantum graphical models and belief propagation
- Quantum invariants of knots and 3-manifolds
- Quantum quandaries: a category-theoretic perspective
- Relative entropy and the Wigner-Yanase-Dyson-Lieb concavity in an interpolation theory
- Reversing quantum dynamics with near-optimal quantum and classical fidelity
- Structure of states which satisfy strong subadditivity of quantum entropy with equality
- Teleportation in general probalistic theories
- The geometry of tensor calculus. I
Cited in
(23)- A quantum Bayes' rule and related inference
- QUANTUM-LIKE REPRESENTATION OF NON-BAYESIAN INFERENCE
- A non-commutative Bayes' theorem
- The weirdness theorem and the origin of quantum paradoxes
- A predicate/state transformer semantics for Bayesian learning
- Multinomial and hypergeometric distributions in Markov categories
- Quantum theory and determinism
- A synthetic approach to Markov kernels, conditional independence and theorems on sufficient statistics
- Diagrammatic Representation and Inference
- Conditional distributions for quantum systems
- Quantum Bayesian nets
- Towards a categorical account of conditional probability
- Causal inference via string diagram surgery. A diagrammatic approach to interventions and counterfactuals
- Free gs-monoidal categories and free Markov categories
- Bayesian generalized probability calculus for density matrices
- DisCoPy: monoidal categories in Python
- The Mathematics of Text Structure
- Models in quantum computing: a systematic review
- Compositional quantum logic
- Disintegration and Bayesian inversion via string diagrams
- scientific article; zbMATH DE number 7449983 (Why is no real title available?)
- Non-commutative disintegrations: existence and uniqueness in finite dimensions
- Fast tests for probing the causal structure of quantum processes
This page was built for publication: Picturing classical and quantum Bayesian inference
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q383002)
