Quantum learning of classical stochastic processes: the completely positive realization problem
From MaRDI portal
Operator spaces and completely bounded maps (46L07) Diagnostics, and linear inference and regression (62J20) Inference from stochastic processes and fuzziness (62M86) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Quantum computation (81P68) Quantum control (81Q93) Quantum stochastic calculus (81S25)
Abstract: Among several tasks in Machine Learning, a specially important one is that of inferring the latent variables of a system and their causal relations with the observed behavior. Learning a Hidden Markov Model of given stochastic process is a textbook example, known as the positive realization problem (PRP). The PRP and its solutions have far-reaching consequences in many areas of systems and control theory, and positive systems theory. We consider the scenario where the latent variables are quantum states, and the system dynamics is constrained only by physical transformations on the quantum system. The observable dynamics is then described by a quantum instrument, and the task is to determine which quantum instrument --if any-- yields the process at hand by iterative application. We take as starting point the theory of quasi-realizations, whence a description of the dynamics of the process is given in terms of linear maps on state vectors and probabilities are given by linear functionals on the state vectors. This description, despite its remarkable resemblance with the Hidden Markov Model, or the iterated quantum instrument, is nevertheless devoid of any stochastic or quantum mechanical interpretation, as said maps fail to satisfy any positivity conditions. The Completely-Positive realization problem then consists in determining whether an equivalent quantum mechanical description of the same process exists. We generalize some key results of stochastic realization theory, and show that the problem has deep connections with operator systems theory, yielding possible insight to the lifting problem in quotient operator systems. Our results have potential applications in quantum machine learning, device-independent characterization and reverse-engineering of stochastic processes and quantum processors, and dynamical processes with quantum memory.
Recommendations
- Quantum Learning of Classical Stochastic Processes: The Completely-Positive Realization Problem
- Machine learning versus semidefinite programming approach to a particular problem of the theory of open quantum systems
- Quantum hidden Markov models based on transition operation matrices
- Abductive learning of quantized stochastic processes with probabilistic finite automata
- scientific article; zbMATH DE number 6096711
Cites work
- A Tutorial on the Positive Realization Problem
- Attempt of an axiomatic foundation fo quantum mechanics and more general theories. II
- Bell inequalities and entanglement
- Control of open quantum systems: case study of the central spin model
- Equivalence classes and local asymptotic normality in system identification for quantum Markov chains
- Finitely correlated states on quantum spin chains
- Functions of Markov Chains
- Generalized probabilistic theories and conic extensions of polytopes
- scientific article; zbMATH DE number 5989818 (Why is no real title available?)
- scientific article; zbMATH DE number 3230998 (Why is no real title available?)
- scientific article; zbMATH DE number 3238722 (Why is no real title available?)
- Irreducible Realizations and the Degree of a Rational Matrix
- Learning Hidden Markov Models Using Nonnegative Matrix Factorization
- Lifts of Convex Sets and Cone Factorizations
- Linear vs. semidefinite extended formulations
- Noncommutative Markov chains associated to a preassigned evolution: an application to the quantum theory of measurement
- On some questions of rationality and decidability
- Operator system quotients of matrix algebras and their tensor products
- Positive matrix factorization via extremal polyhedral cones
- Quotients, exactness, and nuclearity in the operator system category
- Separability Criterion for Density Matrices
- Separability of mixed states: necessary and sufficient conditions.
- Statistical Structure of Quantum Theory
- Sufficient and necessary conditions for semidefinite representability of convex hulls and sets
- Sufficient Conditions for a Stationary Process to be a Function of a Finite Markov Chain
- The complete realization problem for hidden Markov models: a survey and some new results
- The realization problem for hidden Markov models
Cited in
(6)- Machine learning versus semidefinite programming approach to a particular problem of the theory of open quantum systems
- Abductive learning of quantized stochastic processes with probabilistic finite automata
- Quantum Learning of Classical Stochastic Processes: The Completely-Positive Realization Problem
- scientific article; zbMATH DE number 6096711 (Why is no real title available?)
- Quantum learning: asymptotically optimal classification of qubit states
- Quantum theory in finite dimension cannot explain every general process with finite memory
This page was built for publication: Quantum learning of classical stochastic processes: the completely positive realization problem
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2786625)
