Learning large-margin halfspaces with more malicious noise
| 
76 | 
44 | 
0
Abstract
We describe a simple algorithm that runs in time 
and learns an unknown n-dimensional 
-margin halfspace to accuracy 
in theppresence of malicious noise, when the noise rate is allowed to be as high as 
Previous efficient algorithms could only learn to accuracy 
in the presence of malicious noise of rate at most
Our algorithm does not work by optimizing a convex loss function. We show that no algorithm for learning 
-margin halfspaces that minimizes a convex proxy for misclassification error can tolerate malicious noise at a rate greater than 
this may partially explain why previous algorithms could not achieve the higher noise tolerance of our new algorithm.
还没有评论，说两句吧！
热门资源
The Variational S...
Unlike traditional images which do not offer in...
Learning to Predi...
Much of model-based reinforcement learning invo...
Stratified Strate...
In this paper we introduce Stratified Strategy ...
A Mathematical Mo...
Direct democracy, where each voter casts one vo...
Rating-Boosted La...
The performance of a recommendation system reli...
智能在线
400-630-6780
聆听.建议反馈
E-mail: support@tusaishared.com
资源分类
