Theory-inspired path-regularized differential network architecture search
Despite its high search efficiency, differential architecture search (DARTS) often selects network architectures with dominated skip connections which lead to performance degradation. However, theoretical understandings on this issue remain absent, hindering the development of more advanced methods...
Saved in:
Main Authors: | ZHOU, Pan, XIONG, Caiming, SOCHER, Richard, HOI, Steven C. H. |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8998 https://ink.library.smu.edu.sg/context/sis_research/article/10001/viewcontent/2020_NeurIPS_NAS__1_.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Neural architecture search as sparse supernet
by: WU, Y., et al.
Published: (2021) -
Neural architecture search of SPD manifold networks
by: SUKTHANKER, R.S., et al.
Published: (2021) -
Towards theoretically understanding why SGD generalizes better than ADAM in deep learning
by: ZHOU, Pan, et al.
Published: (2020) -
A prototype for palm print identity verification using hierarchical neural network architecture
by: Didulo, Dennis L.
Published: (1999) -
New insight into hybrid stochastic gradient descent: Beyond with-replacement sampling and convexity
by: ZHOU, Pan, et al.
Published: (2018)