Poster
Minimizing Quadratic Functions in Constant Time
Kohei Hayashi · Yuichi Yoshida
Area 5+6+7+8 #171
Keywords: [ Kernel Methods ] [ Large Scale Learning and Big Data ]
Abstract:
A sampling-based optimization method for quadratic functions is proposed. Our method approximately solves the following -dimensional quadratic minimization problem in constant time, which is independent of : , where is a matrix and are vectors. Our theoretical analysis specifies the number of samples such that the approximated solution satisfies with probability . The empirical performance (accuracy and runtime) is positively confirmed by numerical experiments.
Chat is not available.