Tensor networks and efficient descriptions of classical data

2021-03-11 · Sirui Lu, Márton Kanász-Nagy, Ivan Kukuljan, J. Ignacio Cirac

We investigate the potential of tensor network based machine learning methods to scale to large image and text data sets. For that, we study how the mutual information between a subregion and its complement scales with the subsystem size $L$, similarly to how it is done in quantum many-body physics. We find that for text, the mutual information scales as a power law $L^\nu$ with a close to volume law exponent, indicating that text cannot be efficiently described by 1D tensor networks. For images, the scaling is close to an area law, hinting at 2D tensor networks such as PEPS could have an adequate expressibility. For the numerical analysis, we introduce a mutual information estimator based on autoregressive networks, and we also use convolutional neural networks in a neural estimator method.

📄 PDF Abstract BibTeX arXiv:2103.06872

Code (0)

등록된 구현이 없습니다.

Tasks

Tensor Networks

Quantum-Classical Machine learning by Hybrid Tensor Networks

2020-05-15 · Ding Liu, Jiaqi Yao, Zekun Yao, Quan Zhang

Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combin…

BIG-bench Machine Learning Deep Learning Tensor Networks

Number-State Preserving Tensor Networks as Classifiers for Supervised Learning

2019-05-15 · Glen Evenbly

We propose a restricted class of tensor network state, built from number-state preserving tensors, for supervised learning tasks. This class of tensor network is argued to be a natural choice for classifiers as (i) they …

Tensor Networks

Classical and Quantum Algorithms for Tensor Principal Component Analysis

2019-07-30 · M. B. Hastings

We present classical and quantum algorithms based on spectral methods for a problem in tensor principal component analysis. The quantum algorithm achieves a quartic speedup while using exponentially smaller space than th…

Entanglement is Half the Story: Post-Selection vs. Partial Traces

2026-05-04 · Gustav J L Jäger, Krzysztof Bieniasz, Martin B Plenio, Hans-Martin Rieser arxiv

While tensor networks have their traditional application in simulating quantum systems, in the recent decade they have gathered interest as machine learning models. We combine the experience from both fields and derive h…

Quantum Machine Learning

Quantum Machine Learning Tensor Network States

2018-04-06 · Andrey Kardashin, Alexey Uvarov, Jacob Biamonte

Tensor network algorithms seek to minimize correlations to compress the classical data representing quantum states. Tensor network algorithms and similar tools---called tensor network methods---form the backbone of moder…

BIG-bench Machine Learning Quantum Machine Learning Tensor Networks