Competitive on-line prediction (also known as universal prediction of individual sequences) is a strand of learning theory avoiding making any stochastic assumptions about the way...
Abstract— The paper deals with estimating transfer functions of stable linear time-invariant systems under stochastic assumptions. We adopt a nonparametric minimax approach for m...
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
Sequential pattern mining is an active field in the domain of knowledge discovery. Recently, with the constant progress in hardware technologies, real-world databases tend to gro...
We consider the filter generator over GF(2m ) consisting of a linear feedback shift register of length k that generates a maximal length linear sequence of period 2mk − 1 over G...