This content will become publicly available on October 29, 2025
Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
- Award ID(s):
- 1931978
- PAR ID:
- 10565046
- Publisher / Repository:
- arXiv:2311.05139v2 [cs.LG]
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
No document suggestions found