Supplementary material: Gaussian process nonparametric tensor estimator and its minimax optimality
نویسندگان
چکیده
In this supplementary material, we give the comprehensive proof and the generalized theorems. We consider a more general regression setting: yi = f (xi) + i, (S-1) where f : X → R is the unknown true function. We suppose that the true function f is well approximated by f∗ = ∑d∗ r=1 ∏K k=1 f ∗ r (k) (that is f ' f∗). When f = f∗, this generalized regression problem is equivalent to that in the main body. In that sense, the model (S-1) contains the model in the main body as a special setting f = f∗.
منابع مشابه
Gaussian process nonparametric tensor estimator and its minimax optimality
We investigate the statistical efficiency of a nonparametric Gaussian process method for a nonlinear tensor estimation problem. Low-rank tensor estimation has been used as a method to learn higher order relations among several data sources in a wide range of applications, such as multitask learning, recommendation systems, and spatiotemporal analysis. We consider a general setting where a commo...
متن کاملOn the Minimax Optimality of Block Thresholded Wavelets Estimators for ?-Mixing Process
We propose a wavelet based regression function estimator for the estimation of the regression function for a sequence of ?-missing random variables with a common one-dimensional probability density function. Some asymptotic properties of the proposed estimator based on block thresholding are investigated. It is found that the estimators achieve optimal minimax convergence rates over large class...
متن کاملMinimax Optimal Alternating Minimization for Kernel Nonparametric Tensor Learning
We investigate the statistical performance and computational efficiency of the alternating minimization procedure for nonparametric tensor learning. Tensor modeling has been widely used for capturing the higher order relations between multimodal data sources. In addition to a linear model, a nonlinear tensor model has been received much attention recently because of its high flexibility. We con...
متن کاملDoubly Decomposing Nonparametric Tensor Regression
Nonparametric extension of tensor regression is proposed. Nonlinearity in a high-dimensional tensor space is broken into simple local functions by incorporating low-rank tensor decomposition. Compared to naive nonparametric approaches, our formulation considerably improves the convergence rate of estimation while maintaining consistency with the same function class under specific conditions. To...
متن کامل