paper-with-me

Papers

Accelerating Training using Tensor Decomposition

2019-09-10 · Mostafa Elhoushi, Ye Henry Tian, Zihao Chen, Farhan Shafiq, Joey Yiwei Li

Tensor decomposition is one of the well-known approaches to reduce the latency time and number of parameters of a pre-trained model. However, in this paper, we propose an approach to use tensor decomposition to reduce training time of training a model from scratch. In our approach, we train the model from scratch (i.e., randomly initialized weights) with its original architecture for a small number of epochs, then the model is decomposed, and then continue training the decomposed model till the end. There is an optional step in our approach to convert the decomposed architecture back to the original architecture. We present results of using this approach on both CIFAR10 and Imagenet datasets, and show that there can be upto 2x speed up in training time with accuracy drop of upto 1.5% only, and in other cases no accuracy drop. This training acceleration approach is independent of hardware and is expected to have similar speed ups on both CPU and GPU platforms.

📄 PDF Abstract BibTeX arXiv:1909.05675

Code (1)

mostafaelhoushi/tensor-decompositions 공식 구현 pytorch

Tasks

CPUGPUTensor Decomposition

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Accelerating the Low-Rank Decomposed Models

2024-07-24 · Habib Hajimolahoseini, Walid Ahmed, Austin Wen, Yang Liu

Tensor decomposition is a mathematically supported technique for data compression. It consists of applying some kind of a Low Rank Decomposition technique on the tensors or matrices in order to reduce the redundancy of t…

Data CompressionTensor Decomposition

Towards Programmable Memory Controller for Tensor Decomposition

2022-07-17 · Sasindu Wijeratne, Ta-Yang Wang, Rajgopal Kannan, Viktor Prasanna

Tensor decomposition has become an essential tool in many data science applications. Sparse Matricized Tensor Times Khatri-Rao Product (MTTKRP) is the pivotal kernel in tensor decomposition algorithms that decompose high…

Tensor Decomposition

AID-DTI: Accelerating High-fidelity Diffusion Tensor Imaging with Detail-Preserving Model-based Deep Learning

2024-01-03 · Wenxin Fan, Jian Cheng, Cheng Li, Xinrui Ma 외

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps es…

ReLATE: Accelerating Tensor Decomposition via Safe and Efficient Learning of Sparse Encodings

2025-08-29 · Ahmed E. Helal, Fabio Checconi, Jan Laukemann, Yongseok Soh 외 arxiv

Tensor decomposition (TD) is essential for analyzing high-dimensional sparse data, yet its irregular computations and memory-access patterns pose major performance challenges on modern parallel processors. Prior works re…

Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent

2025-01-03 · Tong Wu

Tensors, which give a faithful and effective representation to deliver the intrinsic structure of multi-dimensional data, play a crucial role in an increasing number of signal processing and machine learning problems. Ho…