New query-time bound of tilde O(d + epsilon Delta squared + 1/epsilon cubed) for Gaussian kernel mean estimation, improving prior bounds for small epsilon and intermediate diameter via a fast spherical embedding theorem.
International Conference on Machine Learning , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DS 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
New Bounds for Kernel Sums via Fast Spherical Embeddings
New query-time bound of tilde O(d + epsilon Delta squared + 1/epsilon cubed) for Gaussian kernel mean estimation, improving prior bounds for small epsilon and intermediate diameter via a fast spherical embedding theorem.