Spectral tensor train parameterization of deep learning layers
We study low-rank parameterizations of weight matrices with embedded spectral properties in the Deep Learning context. The low-rank property leads to parameter efficiency and permits taking computational shortcuts when computing mappings. Spectral properties are often subject to constraints in optim...
Saved in:
Main Authors: | OBUKHOV, A., RAKHUBA, M., LINIGER, A., HUANG, Zhiwu, GEORGOULIS, S., DAI, D., VAN Gool L. |
---|---|
格式: | text |
語言: | English |
出版: |
Institutional Knowledge at Singapore Management University
2021
|
主題: | |
在線閱讀: | https://ink.library.smu.edu.sg/sis_research/6259 https://ink.library.smu.edu.sg/context/sis_research/article/7262/viewcontent/Spectral_Tensor_Train_Parameterization_of_Deep_Learning_Layers.pdf |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Singapore Management University |
語言: | English |
相似書籍
-
Building deep networks on grassmann manifolds
由: HUANG, Zhiwu, et al.
出版: (2018) -
Outlier-robust tensor PCA
由: ZHOU, Pan, et al.
出版: (2016) -
Weakly-supervised deep anomaly detection with pairwise relation learning
由: PANG, Guansong, et al.
出版: (2019) -
Deep multi-task learning for depression detection and prediction in longitudinal data
由: PANG, Guansong, et al.
出版: (2020) -
Alignment-enriched tuning for patch-level pre-trained document image models
由: WANG, Lei, et al.
出版: (2023)