paper-with-me

Papers

Deep tensor networks with matrix product operators

2022-09-16 · Bojan Žunkovič

We introduce deep tensor networks, which are exponentially wide neural networks based on the tensor network representation of the weight matrices. We evaluate the proposed method on the image classification (MNIST, FashionMNIST) and sequence prediction (cellular automata) tasks. In the image classification case, deep tensor networks improve our matrix product state baselines and achieve 0.49% error rate on MNIST and 8.3% error rate on FashionMNIST. In the sequence prediction case, we demonstrate an exponential improvement in the number of parameters compared to the one-layer tensor network methods. In both cases, we discuss the non-uniform and the uniform tensor network models and show that the latter generalizes well to different input sizes.

📄 PDF Abstract BibTeX arXiv:2209.09098

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage ClassificationTensor Networks

Similar Papers 제목 키워드 기반

Projected Tensor-Tensor Products for Efficient Computation of Optimal Multiway Data Representations

2024-09-28 · Katherine Keegan, Elizabeth Newman

Tensor decompositions have become essential tools for feature extraction and compression of multiway data. Recent advances in tensor operators have enabled desirable properties of standard matrix algebra to be retained f…

(MPO)$^2$: Multivariate Polynomial Optimization based on Matrix Product Operators

2026-07-17 · Niccolò Ciolli, Anders Vestergaard Nørskov, Michael Kastoryano, Petr Taborsky 외 arxiv

Central to machine learning and signal processing is the ability to perform universal function approximation and learn complex input-output relationships from limited numbers of observations. Multivariate polynomial mode…

Stable Tensor Neural Networks for Rapid Deep Learning

2018-11-15 · Elizabeth Newman, Lior Horesh, Haim Avron, Misha Kilmer

We propose a tensor neural network ($t$-NN) framework that offers an exciting new paradigm for designing neural networks with multidimensional (tensor) data. Our network architecture is based on the $t$-product (Kilmer a…

Deep Learning

Graph Edge Representation via Tensor Product Graph Convolutional Representation

2024-06-21 · Bo Jiang, Sheng Ge, Ziyan Zhang, Beibei Wang 외

Graph Convolutional Networks (GCNs) have been widely studied. The core of GCNs is the definition of convolution operators on graphs. However, existing Graph Convolution (GC) operators are mainly defined on adjacency matr…

Graph Learning

Exact epidemic models from a tensor product formulation

2021-02-23 · Wout Merbis

A general framework for obtaining exact transition rate matrices for stochastic systems on networks is presented and applied to many well-known compartmental models of epidemiology. The state of the population is describ…

Epidemiology