76 search results - page 14 / 16 » Agnostically Learning Halfspaces |
FOCS
2009
IEEE
13 years 4 months ago
2009
IEEE
We give a new model of learning motivated by smoothed analysis (Spielman and Teng, 2001). In this model, we analyze two new algorithms, for PAC-learning DNFs and agnostically learn...
COLT
2007
Springer
13 years 10 months ago
2007
Springer
Abstract. The classical perceptron algorithm is an elementary algorithm for solving a homogeneous linear inequality system Ax > 0, with many important applications in learning t...
FOCS
2008
IEEE
14 years 1 months ago
2008
IEEE
Learning problems form an important category of computational tasks that generalizes many of the computations researchers apply to large real-life data sets. We ask: what concept ...
COLT
2010
Springer
13 years 4 months ago
2010
Springer
In 1994, Y. Mansour conjectured that for every DNF formula on n variables with t terms there exists a polynomial p with tO(log(1/)) non-zero coefficients such that Ex{0,1}n [(p(x)...
STOC
2003
ACM
14 years 7 months ago
2003
ACM
A real multivariate polynomial p(x1, . . . , xn) is said to sign-represent a Boolean function f : {0, 1}n {-1, 1} if the sign of p(x) equals f(x) for all inputs x {0, 1}n. We gi...