Limited memory predictors with compact explicit representations
The paper presents limited memory time-invariant linear integral predictors for continuous time processes such that the corresponding predicting kernels have bounded support. It is shown that processes with exponentially decaying Fourier transforms are predictable with these predictors in some weak sense, meaning that convolution integrals over the future times can be approximated by causal convolutions over past times. The predictors allow a compact explicit represenation via polynomials approximating a periodic exponent in weighted L_2-spaces.
READ FULL TEXT