Patch-level Routing in Mixture-of-Experts is Provably Sample-efficient for Convolutional Neural Networks
- Award ID(s):
- 1932196
- PAR ID:
- 10477237
- Publisher / Repository:
- Proc. of 2023 International Conference on Machine Learning (ICML)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found
An official website of the United States government
