Modeling Sequences with Quantum States: A Look Under the Hood

10/16/2019
by   Tai-Danae Bradley, et al.
0

Classical probability distributions on sets of sequences can be modeled using quantum states. Here, we do so with a quantum state that is pure and entangled. Because it is entangled, the reduced densities that describe subsystems also carry information about the complementary subsystem. This is in contrast to the classical marginal distributions on a subsystem in which information about the complementary system has been integrated out and lost. A training algorithm based on the density matrix renormalization group (DMRG) procedure uses the extra information contained in the reduced densities and organizes it into a tensor network model. An understanding of the extra information contained in the reduced densities allow us to examine the mechanics of this DMRG algorithm and study the generalization error of the resulting model. As an illustration, we work with the even-parity dataset and produce an estimate for the generalization error as a function of the fraction of the dataset used in training.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/12/2020

At the Interface of Algebra and Statistics

This thesis takes inspiration from quantum physics to investigate mathem...
12/30/2021

Quantum Operads

The most standard description of symmetries of a mathematical structure ...
05/22/2018

Universal discriminative quantum neural networks

Quantum mechanics fundamentally forbids deterministic discrimination of ...
11/22/2021

Sublinear quantum algorithms for estimating von Neumann entropy

Entropy is a fundamental property of both classical and quantum systems,...
10/30/2018

Constraints on Multipartite Quantum Entropies

The von Neumann entropy plays a vital role in quantum information theory...
08/04/2017

The physical structure of grammatical correlations: equivalences, formalizations and consequences

In this paper we consider some well-known facts in syntax from a physics...
01/18/2016

Domain based classification

The majority of traditional classification ru les minimizing the expecte...