Supervised Learning with Quantum-Inspired Tensor Networks (2016-05-18T00:00:00.000000Z)

TL;DR

It is demonstrated how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images.

Abstract

Tensor networks are efficient representations of high-dimensional tensors which have been very successful for physics and mathematics applications. We demonstrate how algorithms for optimizing such networks can be adapted to supervised learning tasks by using matrix product states (tensor trains) to parameterize models for classifying images. For the MNIST data set we obtain less than 1% test set classification error. We discuss how the tensor network form imparts additional structure to the learned model and suggest a possible generative interpretation.

Authors

D. Schwab

3 papers

E. Stoudenmire

1 papers

TL;DR

Abstract

Authors

References53 items

Exponential Machines

Machine learning phases of matter

Hand-waving and interpretive dance: an introductory course on tensor networks

Quantum Boltzmann Machine

Tensorizing Neural Networks

Compression of correlation matrices and an efficient method for forming matrix product states of fermionic Gaussian states

Optimal Feature Extraction and Classification of Tensors via Matrix Product State Decomposition

Tensor Network Renormalization.

An exact mapping between the Variational Renormalization Group and Deep Learning

Machine learning for many-body physics: The case of the Anderson impurity model

Tensor Networks for Big Data Analytics and Large-Scale Optimization Problems

Accelerating materials property predictions using machine learning

A tensor approach to learning mixed membership community models

Real Space Renormalization in Statistical Mechanics

Real-space parallel density matrix renormalization group

Tensor decompositions for learning latent variable models

The Alternating Linear Scheme for Tensor Optimization in the Tensor Train Format

Data mining for materials: Computational experiments with AB compounds

Perfect Sampling with Unitary Tensor Networks

Finding Density Functionals with Machine Learning

A Kernel-Based Framework for Learning Graded Relations From Data

Fast and accurate modeling of molecular atomization energies with machine learning.

Tensor-Train Decomposition

Tensor Network States and Geometry

Studying Two Dimensional Systems With the Density Matrix Renormalization Group

Multifactor Expectation Maximization for Factor Graphs

The density-matrix renormalization group in the age of matrix product states

Finding Nature’s Missing Ternary Oxide Compounds Using Machine Learning and Density Functional Theory

Information, Physics, and Computation

Algorithms for entanglement renormalization

Predicting crystal structure by merging data mining with quantum mechanics

A Fast Learning Algorithm for Deep Belief Nets

Entanglement renormalization.

A statistical physics approach for the analysis of machine learning algorithms on real data

Renormalization algorithms for Quantum-Many Body Systems in two and higher dimensions

Density matrix renormalization group and periodic boundary conditions: a quantum information perspective.

Book Review: Statistical Mechanics of Learning. By A. Engel and C. Van den Broeck, Cambridge University Press

Statistical Mechanics of Learning

An introduction to kernel-based learning algorithms

Thermodynamic limit of density matrix renormalization.

Density matrix formulation for quantum renormalization groups.

Statistical mechanics of learning from examples.

An Exactly Solvable Asymmetric Neural Network Model

Information storage in neural networks with low levels of activity.

Spin-glass models of neural networks.

Neural networks and physical systems with emergent collective computational abilities.

Anton Osokin, and Dmitry Vetrov

Neural Networks and Deep Learning (Determination

Tensor decompositions for feature extraction and classification of high dimensional datasets

The Nature of Statistical Learning Theory

“Find-ing

MNIST handwritten digit database

ITensor Library

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names