Additive Sparse Grid Fitting
نویسنده
چکیده
We propose an iterative algorithm for high-dimensional sparse grid regression with penalty. The algorithm is of additive Schwarz type and is thus parallel. We show that the convergence of the algorithm is better than additive Schwarz and examples demonstrate that convergence is between that of additive Schwarz and multiplicative Schwarz procedures. Similarly, the method shows improved performance compared to (additive) iterative methods based on the combination technique. §
منابع مشابه
On additive Schwarz preconditioners for sparse grid discretizations
Based on the framework of subspace splitting and the additive Schwarz scheme, we give bounds for the condition number of multilevel preconditioners for sparse grid discretizations of elliptic model problems. For a BXP-like preconditioner we derive an estimate of the optimal order O(1) and for a HB-like variant we obtain an estimate of the order O(k · 2), where k denotes the number of levels emp...
متن کاملInteraction models for functional regression
A functional regression model with a scalar response and multiple functional predictors is proposed that accommodates two-way interactions in addition to their main effects. The proposed estimation procedure models the main effects using penalized regression splines, and the interaction effect by a tensor product basis. Extensions to generalized linear models and data observed on sparse grids o...
متن کاملSpAM: Sparse Additive Models
We present a new class of models for high-dimensional nonparametric regression and classification called sparse additive models (SpAM). Our methods combine ideas from sparse linear modeling and additive nonparametric regression. We derive a method for fitting the models that is effective even when the number of covariates is larger than the sample size. A statistical analysis of the properties ...
متن کاملMultidimensional Smoothing Using Hyperbolic Interpolatory Wavelets
Abstract. We propose the application of hyperbolic interpolatory wavelets for large-scale -dimensional data fitting. In particular, we show how wavelets can be used as a highly efficient tool for multidimensional smoothing. The grid underlying these wavelets is a sparse grid. The hyperbolic interpolatory wavelet space of level uses basis functions and it is shown that under sufficient smoothnes...
متن کاملSparse Additive Models
We present a new class of methods for high-dimensional nonparametric regression and classification called sparse additive models (SpAM). Our methods combine ideas from sparse linear modeling and additive nonparametric regression. We derive an algorithm for fitting the models that is practical and effective even when the number of covariates is larger than the sample size. SpAM is essentially a ...
متن کامل