English
Related papers

Related papers: Active learning of tree tensor networks using opti…

200 papers

Deep neural networks (DNNs) have delivered a remarkable performance in many tasks of computer vision. However, over-parameterized representations of popular architectures dramatically increase their computational complexity and storage…

Computer Vision and Pattern Recognition · Computer Science 2022-05-31 Chang Nie , Huan Wang , Lu Zhao

Weighted least squares polynomial approximation uses random samples to determine projections of functions onto spaces of polynomials. It has been shown that, using an optimal distribution of sample locations, the number of samples required…

Numerical Analysis · Mathematics 2017-10-10 Abdul-Lateef Haji-Ali , Fabio Nobile , Raúl Tempone , Sören Wolfers

This paper presents the Tensor Product Network (TPNet), a novel neural architecture for efficient and accurate function approximation and PDE solving. The core of the proposal involves constructing the solution explicitly as a linear…

Machine Learning · Computer Science 2026-05-29 Qihong Yang , Yangtao Deng , Qiaolin He , Shiquan Zhang

Deep neural networks (DNNs) achieve impressive results for complicated tasks like object detection on images and speech recognition. Motivated by this practical success, there is now a strong interest in showing good theoretical properties…

Machine Learning · Statistics 2020-06-16 Michael Kohler , Adam Krzyzak , Sophie Langer

Neural networks, a central tool in machine learning, have demonstrated remarkable, high fidelity performance on image recognition and classification tasks. These successes evince an ability to accurately represent high dimensional…

Machine Learning · Statistics 2023-02-08 Grant M. Rotskoff , Eric Vanden-Eijnden

In this paper, we introduce adaptive neuron enhancement (ANE) method for the best least-squares approximation using two-layer ReLU neural networks (NNs). For a given function f(x), the ANE method generates a two-layer ReLU NN and a…

Numerical Analysis · Mathematics 2022-01-19 Min Liu , Zhiqiang Cai , Jingshuang Chen

Given any domain $X\subseteq \mathbb{R}^d$ and a probability measure $\rho$ on $X$, we study the problem of approximating in $L^2(X,\rho)$ a given function $u:X\to\mathbb{R}$, using its noiseless pointwise evaluations at random samples. For…

Numerical Analysis · Mathematics 2019-07-11 Giovanni Migliorati

The low multilinear rank approximation, also known as the truncated Tucker decomposition, has been extensively utilized in many applications that involve higher-order tensors. Popular methods for low multilinear rank approximation usually…

Numerical Analysis · Mathematics 2021-04-05 Chuanfu Xiao , Chao Yang , Min Li

Most stochastic gradient descent algorithms can optimize neural networks that are sub-differentiable in their parameters; however, this implies that the neural network's activation function must exhibit a degree of continuity which limits…

Neural and Evolutionary Computing · Computer Science 2021-12-16 Anastasis Kratsios , Behnoosh Zamanlooy

Deep neural networks (DNNs) are powerful machine learning models and have succeeded in various artificial intelligence tasks. Although various architectures and modules for the DNNs have been proposed, selecting and designing the…

Neural and Evolutionary Computing · Computer Science 2018-01-24 Shinichi Shirakawa , Yasushi Iwata , Youhei Akimoto

This paper introduces a tensor neural network (TNN) to address nonparametric regression problems, leveraging its distinct sub-network structure to effectively facilitate variable separation and enhance the approximation of complex,…

Machine Learning · Statistics 2024-09-16 Yongxin Li , Yifan Wang , Zhongshuo Lin , Hehu Xie

This paper proposes a new family of algorithms for training neural networks (NNs). These are based on recent developments in the field of non-convex optimization, going under the general name of successive convex approximation (SCA)…

Machine Learning · Statistics 2017-06-16 Simone Scardapane , Paolo Di Lorenzo

Recent work has focused on combining kernel methods and deep learning to exploit the best of the two approaches. Here, we introduce a new architecture of neural networks in which we replace the top dense layers of standard convolutional…

Machine Learning · Computer Science 2019-12-02 Luc Giffon , Stéphane Ayache , Thierry Artières , Hachem Kadri

In this paper, we propose a method for the approximation of the solution of high-dimensional weakly coercive problems formulated in tensor spaces using low-rank approximation formats. The method can be seen as a perturbation of a minimal…

Numerical Analysis · Mathematics 2015-02-13 Marie Billaud-Friess , Anthony Nouy , Olivier Zahm

Tensor train (TT) decomposition is a powerful representation for high-order tensors, which has been successfully applied to various machine learning tasks in recent years. However, since the tensor product is not commutative, permutation of…

Numerical Analysis · Computer Science 2017-05-31 Qibin Zhao , Masashi Sugiyama , Andrzej Cichocki

For a given symmetric tensor, we aim at finding a new one whose symmetric rank is small and that is close to the given one. There exist linear relations among the entries of low rank symmetric tensors. Such linear relations can be expressed…

Numerical Analysis · Mathematics 2017-09-08 Jiawang Nie

In this paper, we investigate effective sketching schemes via sparsification for high dimensional multilinear arrays or tensors. More specifically, we propose a novel tensor sparsification algorithm that retains a subset of the entries of a…

Methodology · Statistics 2017-11-17 Dong Xia , Ming Yuan

Constrained counting is a fundamental problem in artificial intelligence. A promising new algebraic approach to constrained counting makes use of tensor networks, following a reduction from constrained counting to the problem of…

Data Structures and Algorithms · Computer Science 2020-04-29 Jeffrey M. Dudek , Leonardo Dueñas-Osorio , Moshe Y. Vardi

We propose an extension of tree-based space-partitioning indexing structures for data with low intrinsic dimensionality embedded in a high dimensional space. We call this extension an Angle Tree. Our extension can be applied to both…

Data Structures and Algorithms · Computer Science 2010-04-19 Ilia Zvedeniouk , Sanjay Chawla

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
‹ Prev 1 3 4 5 6 7 10 Next ›