//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
We show that for many classes C we can construct a predictor p that is perfectly C-multiaccurate, yet p is completely uncorrelated with the labels (even though some concepts in C do have high correlation with the labels).