21 citations · 43 across the 10 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.LG2016★ 11 cited
Classification accuracy as a proxy for two sample testing
Ilmun Kim, Aaditya Ramdas, Aarti Singh +1
When data analysts train a classifier and check if its accuracy is significantly different from chance, they are implicitly performing a two-sample test. We investigate the statist…
stat.ML2016
Minimax Lower Bounds for Linear Independence Testing
Aaditya Ramdas, David Isenberg, Aarti Singh +1
Linear independence testing is a fundamental information-theoretic and statistical problem that can be posed as follows: given points from a dimen…