Training a diffusion weight generator with meta-learning and a local-consistency loss lets it hit intermediate optimizer checkpoints on schedule and end at the global optimum.
Generalization bounds for meta-learning: An information-theoretic analysis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Learning to Learn Weight Generation via Local Consistency Diffusion
Training a diffusion weight generator with meta-learning and a local-consistency loss lets it hit intermediate optimizer checkpoints on schedule and end at the global optimum.