Measures of distinguishability between stochastic processes
arXiv:1909.08366 · doi:10.1103/PhysRevE.101.062137
Abstract
Quantifying how distinguishable two stochastic processes are lies at the heart of many fields, such as machine learning and quantitative finance. While several measures have been proposed for this task, none have universal applicability and ease of use. In this Letter, we suggest a set of requirements for a well-behaved measure of process distinguishability. Moreover, we propose a family of measures, called divergence rates, that satisfy all of these requirements. Focussing on a particular member of this family -- the co-emission divergence rate -- we show that it can be computed efficiently, behaves qualitatively similar to other commonly-used measures in their regimes of applicability, and remains well-behaved in scenarios where other measures break down.
References in corpus (23)
- Quantum Computing in the NISQ era and beyond
- A Practical Introduction to Tensor Networks: Matrix Product States and Projected Entangled Pair States
- The iTEBD algorithm beyond unitary evolution
- Computational Mechanics: Pattern and Prediction, Structure and Simplicity
- Unsupervised Generative Modeling Using Matrix Product States
- Equivalence of restricted Boltzmann machines and tensor network states
- Quantum Entanglement in Deep Learning Architectures
- Occam's Quantum Razor: How Quantum Mechanics can reduce the complexity of classical models
- Density Matrix Renormalization Group and Reaction-Diffusion Processes
- Learning Relevant Features of Data with Multi-scale Tensor Networks
- Critical properties of the reaction - diffusion model 2A -> 3A, 2A ->0
- Matrix product operators and states: NP-hardness and undecidability
- Unifying Neural-network Quantum States and Correlator Product States via Tensor Networks
- A practical, unitary simulator for non-Markovian complex processes
- Application of the Density Matrix Renormalization Group Method to a Non-Equilibrium Problem
- Matrix Product Operators for Sequence to Sequence Learning
- Optimal stochastic modelling with unitary quantum dynamics
- Extreme Quantum Advantage for Rare-Event Sampling
- Superior memory efficiency of quantum devices for the simulation of continuous-time stochastic processes
- Matrix Product States for Quantum Stochastic Modelling
- Stochastic Matrix Product States
- Capturing exponential variance using polynomial resources: applying tensor networks to non-equilibrium stochastic processes
- Memory-efficient tracking of complex temporal and symbolic dynamics with quantum simulators