Quantum learning of classical stochastic processes: The Completely-Positive Realization Problem
arXiv:1412.3634 · doi:10.1063/1.4936935
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.
References in corpus (16)
- Separability Criterion for Density Matrices
- Separability of Mixed States: Necessary and Sufficient Conditions
- Non-local correlations as an information theoretic resource
- Lifts of convex sets and cone factorizations
- Occam's Quantum Razor: How Quantum Mechanics can reduce the complexity of classical models
- Quantum System Identification
- Matrix product operators and states: NP-hardness and undecidability
- Robust, self-consistent, closed-form tomography of quantum logic gates on a trapped ion qubit
- Fisher information and asymptotic normality in system identification for quantum Markov chains
- Hidden Quantum Markov Models and non-adaptive read-out of many-body states
- Assessing dimensions from evolution
- 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
- One simple postulate implies that every polytopic state space is classical
- Identifiability of Open Quantum Systems
- Learning Hidden Markov Models using Non-Negative Matrix Factorization
Cited by in corpus (13)
- Extreme dimensionality reduction with quantum modelling
- Matrix Product States for Quantum Stochastic Modelling
- Causal Asymmetry in a Quantum World
- Memory compression and thermal efficiency of quantum implementations of non-deterministic hidden Markov models
- Quantum Process Identification: A Method for Characterizing Non-Markovian Quantum Dynamics
- Quantum Causal Unravelling
- Learning optimal quantum models is NP-hard
- Recommender systems inspired by the structure of quantum theory
- Quantum theory in finite dimension cannot explain every general process with finite memory
- Quantum Tensor Networks, Stochastic Processes, and Weighted Automata
- The Learnability of Unknown Quantum Measurements
- Quantum Dimension Reduction of Hidden Markov Models
- Ideal stochastic process modeling with post-quantum quasiprobabilistic theories