Tensor network to learn the wavefunction of data

Abstract

How many different ways are there to handwrite digit 3? To quantify this question imagine extending a dataset of handwritten digits MNIST by sampling additional images until they start repeating. We call the collection of all resulting images of digit 3 the "full set." To study the properties of the full set we introduce a tensor network architecture which simultaneously accomplishes both classification (discrimination) and sampling tasks. Qualitatively, our trained network represents the indicator function of the full set. It therefore can be used to characterize the data itself. We illustrate that by studying the full sets associated with the digits of MNIST. Using quantum mechanical interpretation of our network we characterize the full set by calculating its entanglement entropy. We also study its geometric properties such as mean Hamming distance, effective dimension, and size. The latter answers the question above -- the total number of black and white threes written MNIST style is $2^{72}$.

References in corpus (9)

• Scaling Laws for Neural Language Models
• Explaining Neural Scaling Laws
• Tree Tensor Networks for Generative Modeling
• TensorNetwork for Machine Learning
• Mutual Information Scaling for Tensor Network Machine Learning
• A Neural Scaling Law from the Dimension of the Data Manifold
• Tensor network language model
• Entanglement and Tensor Networks for Supervised Image Classification
• Language as a matrix product state

Cited by in corpus (4)

• Machine learning with tree tensor networks, CP rank constraints, and tensor dropout
• Deep tensor networks with matrix product operators
• Optimal sampling of tensor networks targeting wave function's fast decaying tails
• Using matrix-product states for time-series machine learning