The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
특이값 분해(SVD)의 빠른 계산은 다양한 기계 학습 작업에서 큰 관심을 끌고 있습니다. 최근 무작위 선형 대수학을 기반으로 한 SVD 방법은 이 영역에서 상당한 속도 향상을 보여주었습니다. 대규모 데이터를 처리하기 위해서는 GPU와 같은 가속기를 갖춘 컴퓨팅 시스템이 주류가 되었습니다. 이러한 시스템에서는 입력 데이터에 대한 액세스가 전체 프로세스 시간을 지배합니다. 따라서 계산을 가속기로 보내려면 코어 외부 알고리즘을 설계해야 합니다. 본 논문에서는 이미지 데이터에서 자주 관찰되는 느린 감쇠 특이 스펙트럼을 갖는 행렬을 위해 설계된 블록 무작위 SVD(BRSVD)라는 정확한 XNUMX패스 무작위 SVD를 제안합니다. BRSVD는 최신 컴퓨팅 시스템 아키텍처의 성능을 최대한 활용하고 병렬 및 코어 외부 방식으로 대규모 데이터를 효율적으로 처리합니다. 우리의 실험에서는 BRSVD가 데이터 전송에서 계산으로 성능 병목 현상을 효과적으로 이동시켜 비슷한 정확도를 유지하면서 속도 측면에서 기존의 무작위 SVD 방법보다 뛰어난 것으로 나타났습니다.
Yuechao LU
Osaka University
Yasuyuki MATSUSHITA
Osaka University
Fumihiko INO
Osaka University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Yuechao LU, Yasuyuki MATSUSHITA, Fumihiko INO, "Block Randomized Singular Value Decomposition on GPUs" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 9, pp. 1949-1959, September 2020, doi: 10.1587/transinf.2019EDP7265.
Abstract: Fast computation of singular value decomposition (SVD) is of great interest in various machine learning tasks. Recently, SVD methods based on randomized linear algebra have shown significant speedup in this regime. For processing large-scale data, computing systems with accelerators like GPUs have become the mainstream approach. In those systems, access to the input data dominates the overall process time; therefore, it is needed to design an out-of-core algorithm to dispatch the computation into accelerators. This paper proposes an accurate two-pass randomized SVD, named block randomized SVD (BRSVD), designed for matrices with a slow-decay singular spectrum that is often observed in image data. BRSVD fully utilizes the power of modern computing system architectures and efficiently processes large-scale data in a parallel and out-of-core fashion. Our experiments show that BRSVD effectively moves the performance bottleneck from data transfer to computation, so that outperforms existing randomized SVD methods in terms of speed with retaining similar accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDP7265/_p
부
@ARTICLE{e103-d_9_1949,
author={Yuechao LU, Yasuyuki MATSUSHITA, Fumihiko INO, },
journal={IEICE TRANSACTIONS on Information},
title={Block Randomized Singular Value Decomposition on GPUs},
year={2020},
volume={E103-D},
number={9},
pages={1949-1959},
abstract={Fast computation of singular value decomposition (SVD) is of great interest in various machine learning tasks. Recently, SVD methods based on randomized linear algebra have shown significant speedup in this regime. For processing large-scale data, computing systems with accelerators like GPUs have become the mainstream approach. In those systems, access to the input data dominates the overall process time; therefore, it is needed to design an out-of-core algorithm to dispatch the computation into accelerators. This paper proposes an accurate two-pass randomized SVD, named block randomized SVD (BRSVD), designed for matrices with a slow-decay singular spectrum that is often observed in image data. BRSVD fully utilizes the power of modern computing system architectures and efficiently processes large-scale data in a parallel and out-of-core fashion. Our experiments show that BRSVD effectively moves the performance bottleneck from data transfer to computation, so that outperforms existing randomized SVD methods in terms of speed with retaining similar accuracy.},
keywords={},
doi={10.1587/transinf.2019EDP7265},
ISSN={1745-1361},
month={September},}
부
TY - JOUR
TI - Block Randomized Singular Value Decomposition on GPUs
T2 - IEICE TRANSACTIONS on Information
SP - 1949
EP - 1959
AU - Yuechao LU
AU - Yasuyuki MATSUSHITA
AU - Fumihiko INO
PY - 2020
DO - 10.1587/transinf.2019EDP7265
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2020
AB - Fast computation of singular value decomposition (SVD) is of great interest in various machine learning tasks. Recently, SVD methods based on randomized linear algebra have shown significant speedup in this regime. For processing large-scale data, computing systems with accelerators like GPUs have become the mainstream approach. In those systems, access to the input data dominates the overall process time; therefore, it is needed to design an out-of-core algorithm to dispatch the computation into accelerators. This paper proposes an accurate two-pass randomized SVD, named block randomized SVD (BRSVD), designed for matrices with a slow-decay singular spectrum that is often observed in image data. BRSVD fully utilizes the power of modern computing system architectures and efficiently processes large-scale data in a parallel and out-of-core fashion. Our experiments show that BRSVD effectively moves the performance bottleneck from data transfer to computation, so that outperforms existing randomized SVD methods in terms of speed with retaining similar accuracy.
ER -