English
Related papers

Related papers: Fast high-dimensional integration using tensor net…

200 papers

Tensor neural networks (TNNs) have demonstrated their superiority in solving high-dimensional problems. However, similar to conventional neural networks, TNNs are also influenced by the Frequency Principle, which limits their ability to…

Machine Learning · Computer Science 2026-05-15 Jizu Huang , Yue Qiu , Rukang You

Recent advances in quasi-Monte Carlo integration demonstrate that the median of linearly scrambled digital net estimators achieves near-optimal convergence rates for high-dimensional integrals without requiring a priori knowledge of the…

Computation · Statistics 2026-02-03 Zexin Pan

We solve high-dimensional steady-state Fokker-Planck equations on the whole space by applying tensor neural networks. The tensor networks are a linear combination of tensor products of one-dimensional feedforward networks or a linear…

Numerical Analysis · Mathematics 2024-11-04 Taorui Wang , Zheyuan Hu , Kenji Kawaguchi , Zhongqiang Zhang , George Em Karniadakis

Most currently used tensor regression models for high-dimensional data are based on Tucker decomposition, which has good properties but loses its efficiency in compressing tensors very quickly as the order of tensors increases, say greater…

Methodology · Statistics 2024-03-20 Yuefeng Si , Yingying Zhang , Yuxi Cai , Chunling Liu , Guodong Li

We construct a rejection-free Monte Carlo method for the hard-disk system. Rejection-free Monte Carlo methods preserve the time-evolution behavior of the standard Monte Carlo method, and this relationship is confirmed for our method by…

Statistical Mechanics · Physics 2015-06-24 H. Watanabe , S. Yukawa , M. A. Novotny , N. Ito

Tensor Network States are ans\"atze for the efficient description of quantum many-body systems. Their success for one dimensional problems, together with the fact that they do not suffer from the sign problem and can address the simulation…

High Energy Physics - Lattice · Physics 2022-09-21 Mari Carmen Bañuls , Krzysztof Cichy , J. Ignacio Cirac , Karl Jansen , Stefan Kühn

Monte Carlo methods are widely used in particle physics to integrate and sample probability distributions (differential cross sections or decay rates) on multi-dimensional phase spaces. We present a Neural Network (NN) algorithm optimized…

High Energy Physics - Phenomenology · Physics 2020-10-21 Matthew D. Klimek , Maxim Perelstein

New machine learning based algorithms have been developed and tested for Monte Carlo integration based on generative Boosted Decision Trees and Deep Neural Networks. Both of these algorithms exhibit substantial improvements compared to…

High Energy Physics - Phenomenology · Physics 2017-07-04 Joshua Bendavid

A new unbiased Monte Carlo technique called Tensor Network Monte Carlo (TNMC) is introduced based on sampling all possible renormalizations (or course-grainings) of tensor networks, in this case matrix-product states. Tensor networks are a…

Statistical Mechanics · Physics 2015-07-06 Andrew J. Ferris

We extend a recently developed method to solve semi-linear PDEs to the case of a degenerated diffusion. Being a pure Monte Carlo method it does not suffer from the so called curse of dimensionality and it can be used to solve problems that…

Probability · Mathematics 2018-05-15 Xavier Warin

Quantum computers are expected to enable fast solving of large-scale combinatorial optimization problems. However, their limitations in fidelity and the number of qubits prevent them from handling real-world problems. Recently, a…

Statistical Mechanics · Physics 2025-07-23 Hyakka Nakada , Kotaro Tanahashi , Shu Tanaka

In this paper, we introduce a tensor neural network based machine learning method for solving the elliptic partial differential equations with random coefficients in a bounded physical domain. With the help of tensor product structure, we…

Numerical Analysis · Mathematics 2024-02-02 Hongtao Chen , Rui Fu , Yifan Wang , Hehu Xie

We construct a tensor network representation of the partition function for the massless Schwinger model on a two dimensional lattice using staggered fermions. The tensor network representation allows us to include a topological term. Using…

High Energy Physics - Lattice · Physics 2020-06-24 Nouman Butt , Simon Catterall , Yannick Meurice , Judah Unmuth-Yockey

Tensor regression has shown to be advantageous in learning tasks with multi-directional relatedness. Given massive multiway data, traditional methods are often too slow to operate on or suffer from memory bottleneck. In this paper, we…

Machine Learning · Computer Science 2016-07-12 Rose Yu , Yan Liu

The computational complexity of simultaneous inference methods in high-dimensional linear regression models quickly increases with the number variables. This paper proposes a computationally efficient method based on the Moore-Penrose…

Statistics Theory · Mathematics 2021-02-02 Tom Boot , Didier Nibbering

Tensor network states are powerful variational ans\"atze for many-body ground states of quantum lattice models. The use of Monte Carlo sampling techniques in tensor network approaches significantly reduces the cost of tensor contractions,…

Strongly Correlated Electrons · Physics 2012-05-01 Andrew J. Ferris , Guifre Vidal

High dimensional integration is essential to many areas of science, ranging from particle physics to Bayesian inference. Approximating these integrals is hard, due in part to the difficulty of locating and sampling from regions of the…

Machine Learning · Statistics 2020-05-25 Thomas Foster , Chon Lok Lei , Martin Robinson , David Gavaghan , Ben Lambert

We consider several issues related to the multidimensional integration using a network of heterogeneous computers. Based on these considerations, we develop a new general purpose scheme which can significantly reduce the time needed for…

Computational Physics · Physics 2009-10-30 S. Veseli

Tensor networks (TNs) and neural networks (NNs) are two fundamental data modeling approaches. TNs were introduced to solve the curse of dimensionality in large-scale tensors by converting an exponential number of dimensions to polynomial…

Machine Learning · Computer Science 2025-03-18 Maolin Wang , Yu Pan , Zenglin Xu , Guangxi Li , Xiangli Yang , Danilo Mandic , Andrzej Cichocki

We propose a novel stochastic algorithm that randomly samples entire rows and columns of the matrix as a way to approximate an arbitrary matrix function using the power series expansion. This contrasts with existing Monte Carlo methods,…

Data Structures and Algorithms · Computer Science 2024-09-23 Nicolas L. Guidotti , Juan A. Acebrón , José Monteiro