Spectral Gradient Surgery disentangles class-discriminative and domain-specific signals in distribution-matching distilled datasets by analyzing gradient agreement in the spectral domain, yielding better out-of-distribution performance.
Proceedings of the International Conference on Machine Learning (ICML) , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
Spectral Gradient Surgery disentangles class-discriminative and domain-specific signals in distribution-matching distilled datasets by analyzing gradient agreement in the spectral domain, yielding better out-of-distribution performance.