Point Location and Active Learning: Learning Halfspaces Almost Optimally

Hopkins Max
Hopkins Max
Mahajan Gaurav
Mahajan Gaurav
Cited by: 0|Bibtex|Views22|Links

Abstract:

Given a finite set $X \subset \mathbb{R}^d$ and a binary linear classifier $c: \mathbb{R}^d \to \{0,1\}$, how many queries of the form $c(x)$ are required to learn the label of every point in $X$? Known as \textit{point location}, this problem has inspired over 35 years of research in the pursuit of an optimal algorithm. Building on the...More

Code:

Data:

Your rating :
0

 

Tags
Comments