Maximum Margin Algorithms with Boolean Kernels

8 years 6 months ago
Maximum Margin Algorithms with Boolean Kernels
Recent work has introduced Boolean kernels with which one can learn linear threshold functions over a feature space containing all conjunctions of length up to k (for any 1 ≤ k ≤ n) over the original n Boolean features in the input space. This motivates the question of whether maximum margin algorithms such as Support Vector Machines can learn Disjunctive Normal Form expressions in the Probably Approximately Correct (PAC) learning model by using this kernel. We study this question, as well as a variant in which structural risk minimization (SRM) is performed where the class hierarchy is taken over the length of conjunctions. We show that maximum margin algorithms using the Boolean kernels do not PAC learn t(n)term DNF for any t(n) = ω(1), even when used with such a SRM scheme. We also consider PAC learning under the uniform distribution and show that if the kernel uses conjunctions of length ˜ω( √ n) then the maximum margin hypothesis will fail on the uniform distribution as ...
Roni Khardon, Rocco A. Servedio
Added 06 Jul 2010
Updated 06 Jul 2010
Type Conference
Year 2003
Where COLT
Authors Roni Khardon, Rocco A. Servedio
Comments (0)