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. |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | 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 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Building deep networks on grassmann manifolds
by: HUANG, Zhiwu, et al.
Published: (2018) -
Outlier-robust tensor PCA
by: ZHOU, Pan, et al.
Published: (2016) -
Weakly-supervised deep anomaly detection with pairwise relation learning
by: PANG, Guansong, et al.
Published: (2019) -
Deep multi-task learning for depression detection and prediction in longitudinal data
by: PANG, Guansong, et al.
Published: (2020) -
Alignment-enriched tuning for patch-level pre-trained document image models
by: WANG, Lei, et al.
Published: (2023)