An adaptive nearest neighbor rule for classification

Akshay Balsubramani, Sanjoy Dasgupta, yoav Freund, Shay Moran

Neural Information Processing Systems 

Findthesmallest0 (n, k, ), where (n, k, )= c1 r logn+ log ( 1/ ) k . Then, withprobabilityatleast1 , theresultingclassifiergn satisfiesthefollowing: foreverypointx 2 supp(µ), if n C adv (x) max log 1 adv (x) , log 1 thengn(x)= g (x).

Similar Docs  Excel Report  more

TitleSimilaritySource
None found