English
Related papers

Related papers: Minimum Cost Loop Nests for Contraction of a Spars…

200 papers

Fully-connected layers in deep neural networks (DNN) are often the throughput and power bottleneck during training. This is due to their large size and low data reuse. Pruning dense layers can significantly reduce the size of these…

Machine Learning · Computer Science 2018-02-13 Mihailo Isakov , Michel A. Kinsy

In the tensor-network framework, the expectation values of two-dimensional quantum states are evaluated by contracting a double-layer tensor network constructed from initial and final tensor-network states. The computational cost of…

Strongly Correlated Electrons · Physics 2017-07-24 Z. Y. Xie , H. J. Liao , R. Z. Huang , H. D. Xie , J. Chen , Z. Y. Liu , T. Xiang

This paper describes a flexible framework for generalized low-rank tensor estimation problems that includes many important instances arising from applications in computational imaging, genomics, and network analysis. The proposed estimator…

Statistics Theory · Mathematics 2021-02-08 Rungang Han , Rebecca Willett , Anru R. Zhang

There is an increasing interest in emulating Spiking Neural Networks (SNNs) on neuromorphic computing devices due to their low energy consumption. Recent advances have allowed training SNNs to a point where they start to compete with…

Neural and Evolutionary Computing · Computer Science 2022-01-14 Nicolas Perez-Nieves , Dan F. M. Goodman

We propose a new method to create compact convolutional neural networks (CNNs) by exploiting sparse convolutions. Different from previous works that learn sparsity in models, we directly employ hand-crafted kernels with regular sparse…

Computer Vision and Pattern Recognition · Computer Science 2018-09-12 Chun-Fu Chen , Quanfu Fan , Marco Pistoia , Gwo Giun Lee

Lossy compression algorithms are typically designed to achieve the lowest possible distortion at a given bit rate. However, recent studies show that pursuing high perceptual quality would lead to increase of the lowest achievable distortion…

Information Theory · Computer Science 2021-06-15 Zeyu Yan , Fei Wen , Rendong Ying , Chao Ma , Peilin Liu

Recurrent Neural Networks (RNNs) are used in state-of-the-art models in domains such as speech recognition, machine translation, and language modelling. Sparsity is a technique to reduce compute and memory requirements of deep learning…

Machine Learning · Computer Science 2017-11-09 Sharan Narang , Eric Undersander , Gregory Diamos

Recurrent Neural Networks (RNNs) are powerful sequence modeling tools. However, when dealing with high dimensional inputs, the training of RNNs becomes computational expensive due to the large number of model parameters. This hinders RNNs…

Machine Learning · Computer Science 2018-05-23 Jinmian Ye , Linnan Wang , Guangxi Li , Di Chen , Shandian Zhe , Xinqi Chu , Zenglin Xu

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

Deep neural networks (DNNs) have been proven to be effective in solving many real-life problems, but its high computation cost prohibits those models from being deployed to edge devices. Pruning, as a method to introduce zeros to model…

Machine Learning · Computer Science 2021-12-22 Fei Sun , Minghai Qin , Tianyun Zhang , Xiaolong Ma , Haoran Li , Junwen Luo , Zihao Zhao , Yen-Kuang Chen , Yuan Xie

Tensor completion aimes at recovering missing data, and it is one of the popular concerns in deep learning and signal processing. Among the higher-order tensor decomposition algorithms, the recently proposed fully-connected tensor network…

Machine Learning · Computer Science 2022-04-07 Peilin Yang , Yonghui Huang , Yuning Qiu , Weijun Sun , Guoxu Zhou

Many recent tensor network algorithms apply unitary operators to parts of a tensor network in order to reduce entanglement. However, many of the previously used iterative algorithms to minimize entanglement can be slow. We introduce an…

Quantum Physics · Physics 2022-01-25 Kevin Slagle

The alternating least squares algorithm for CP and Tucker decomposition is dominated in cost by the tensor contractions necessary to set up the quadratic optimization subproblems. We introduce a novel family of algorithms that uses…

Numerical Analysis · Mathematics 2021-04-15 Linjian Ma , Edgar Solomonik

This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition. We give an algorithm with provable approximation guarantees for its…

Data Structures and Algorithms · Computer Science 2024-06-19 Mehrdad Ghadiri , Matthew Fahrbach , Gang Fu , Vahab Mirrokni

Sparse coding and dictionary learning are popular techniques for linear inverse problems such as denoising or inpainting. However in many cases, the measurement process is nonlinear, for example for clipped, quantized or 1-bit measurements.…

Signal Processing · Electrical Eng. & Systems 2020-01-08 Lucas Rencker , Francis Bach , Wenwu Wang , Mark D. Plumbley

Recent research has focused on accelerating stencil computations by exploiting emerging hardware like Tensor Cores. To leverage these accelerators, the stencil operation must be transformed to matrix multiplications. However, this…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-27 Qiqi GU , Chenpeng Wu , Heng Shi , Jianguo Yao

Sparse tensors are prevalent in many data-intensive applications, yet existing differentiable programming frameworks are tailored towards dense tensors. This presents a significant challenge for efficiently computing gradients through…

Programming Languages · Computer Science 2023-03-14 Amir Shaikhha , Mathieu Huot , Shideh Hashemian

Tensors play a central role in many modern machine learning and signal processing applications. In such applications, the target tensor is usually of low rank, i.e., can be expressed as a sum of a small number of rank one tensors. This…

Machine Learning · Statistics 2015-05-18 Parikshit Shah , Nikhil Rao , Gongguo Tang

The high energy cost of processing deep convolutional neural networks impedes their ubiquitous deployment in energy-constrained platforms such as embedded systems and IoT devices. This work introduces convolutional layers with pre-defined…

Computer Vision and Pattern Recognition · Computer Science 2020-02-06 Souvik Kundu , Mahdi Nazemi , Massoud Pedram , Keith M. Chugg , Peter A. Beerel

Sparsity is a well-studied technique for compressing deep neural networks (DNNs) without compromising performance. In deep reinforcement learning (DRL), neural networks with up to 5% of their original weights can still be trained with…

Machine Learning · Computer Science 2026-02-17 Isam Vrce , Andreas Kassler , Gökçe Aydos