AI RESEARCH
Testing Support Size More Efficiently Than Learning Histograms
arXiv CS.LG
•
ArXi:2410.18915v4 Announce Type: replace-cross Consider two problems about an unknown probability distribution $p$: 1. How many samples from $p$ are required to test if $p$ is ed on $n$ elements or not? Specifically, given samples from $p$, determine whether it is ed on at most $n$ elements, or it is "$\epsilon$-far" (in total variation distance) from being ed on $n$ elements. 2.