Kernel covariance embeddings of non-atomic Borel probability measures on locally compact Polish spaces induce singular centered Gaussians in the RKHS, making equality testing equivalent to singularity testing via the Feldman-Hajek dichotomy.
Do imagenet classifiers generalize to imagenet? InInternational Conference on Machine Learning, pages 5389–5400
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
dataset 1polarities
use dataset 1representative citing papers
VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintaining competitive performance.
citing papers explorer
-
Kernel Embeddings and the Separation of Measure Phenomenon
Kernel covariance embeddings of non-atomic Borel probability measures on locally compact Polish spaces induce singular centered Gaussians in the RKHS, making equality testing equivalent to singularity testing via the Feldman-Hajek dichotomy.
-
Elastic Attention Cores for Scalable Vision Transformers
VECA learns effective visual representations using core-periphery attention where patches interact exclusively via a resolution-invariant set of learned core embeddings, achieving linear O(N) complexity while maintaining competitive performance.