Click here to flash read.
arXiv:2403.00666v3 Announce Type: replace-cross
Abstract: We obtain essentially matching upper and lower bounds for the expected max-sliced 1-Wasserstein distance between a probability measure on a separable Hilbert space and its empirical distribution from $n$ samples. By proving a Banach space version of this result, we also obtain an upper bound, that is sharp up to a log factor, for the expected max-sliced 2-Wasserstein distance between a symmetric probability measure $\mu$ on a Euclidean space and its symmetrized empirical distribution in terms of the operator norm of the covariance matrix of $\mu$ and the diameter of the support of $\mu$.
Click here to read this post out
ID: 809594; Unique Viewers: 0
Unique Voters: 0
Total Votes: 0
Votes:
Latest Change: March 29, 2024, 7:33 a.m.
Changes:
Dictionaries:
Words:
Spaces:
Views: 19
CC:
No creative common's license
No creative common's license
Comments: