In this paper we develop a novel generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning problem reduces to in...
: The classical result in the theory of random graphs, proved by Erd˝os and Rényi in 1960, concerns the threshold for the appearance of the giant component in the random graph pr...
Tom Bohman, Alan M. Frieze, Michael Krivelevich, P...
We propose a novel model to characterize the security of linear blinding techniques. The proposed model relates the security of blinding to the possibility of estimating the blind...
We consider model-free pricing of digital options, which pay out if the underlying asset has crossed both upper and lower barriers. We make only weak assumptions about the underly...
Any valid Ramsey statement n −→ (k)2 2 can be encoded into a DNF formula RAM(n, k) of size O(nk) and with terms of size k 2 . Let rk be the minimal n for which the statement h...