Sciweavers

5 search results - page 1 / 1
» Learning Threshold Functions with Small Weights Using Member...
Sort
View
COLT
1999
Springer
13 years 9 months ago
Learning Threshold Functions with Small Weights Using Membership Queries
We study the learnability of Threshold functions with bounded weights using membership queries only. We show that the class Ct of Threshold functions with positive integer weights...
Elias Abboud, Nader Agha, Nader H. Bshouty, Nizar ...
FOCS
2002
IEEE
13 years 9 months ago
Learning Intersections and Thresholds of Halfspaces
We give the first polynomial time algorithm to learn any function of a constant number of halfspaces under the uniform distribution on the Boolean hypercube to within any constan...
Adam Klivans, Ryan O'Donnell, Rocco A. Servedio
COLT
2006
Springer
13 years 8 months ago
Efficient Learning Algorithms Yield Circuit Lower Bounds
We describe a new approach for understanding the difficulty of designing efficient learning algorithms. We prove that the existence of an efficient learning algorithm for a circui...
Lance Fortnow, Adam R. Klivans
ECCC
2007
86views more  ECCC 2007»
13 years 4 months ago
Testing Halfspaces
This paper addresses the problem of testing whether a Boolean-valued function f is a halfspace, i.e. a function of the form f(x) = sgn(w·x−θ). We consider halfspaces over the ...
Kevin Matulef, Ryan O'Donnell, Ronitt Rubinfeld, R...
FOCS
2005
IEEE
13 years 10 months ago
Lower Bounds for the Noisy Broadcast Problem
We prove the first non-trivial (super linear) lower bound in the noisy broadcast model, defined by El Gamal in [6]. In this model there are n + 1 processors P0, P1, . . . , Pn, ...
Navin Goyal, Guy Kindler, Michael E. Saks