Additive Models with Trend Filtering
نویسندگان
چکیده
We consider additive models built with trend filtering, i.e., additive models whose components are each regularized by the (discrete) total variation of their (k+1)st (discrete) derivative, for a chosen integer k ≥ 0. This results in kth degree piecewise polynomial components, (e.g., k = 0 gives piecewise constant components, k = 1 gives piecewise linear, k = 2 gives piecewise quadratic, etc.). In univariate nonparametric regression, the localized nature of the total variation regularizer used by trend filtering has been shown to produce estimates with superior local adaptivity to those from smoothing splines (and linear smoothers, more generally) (Tibshirani 2014). Further, the structured nature of this regularizer has been shown to lead to highly efficient computational routines for trend filtering (Kim et al. 2009, Ramdas & Tibshirani 2016). In this paper, we argue that both of these properties carry over to the additive models setting. We derive fast error rates for additive trend filtering estimates, and prove that these rates are minimax optimal when the underlying function is itself additive and has component functions whose derivatives are of bounded variation. We show that such rates are unattainable by additive smoothing splines (and by additive models built from linear smoothers, in general). We argue that backfitting provides an efficient algorithm for additive trend filtering, as it is built around the fast univariate trend filtering solvers; moreover, we describe a modified backfitting procedure whose iterations can be run in parallel. Finally, we conduct experiments to examine the empirical properties of additive trend filtering, and outline some possible extensions.
منابع مشابه
Using generalized additive (mixed) models to analyze single case designs.
This article shows how to apply generalized additive models and generalized additive mixed models to single-case design data. These models excel at detecting the functional form between two variables (often called trend), that is, whether trend exists, and if it does, what its shape is (e.g., linear and nonlinear). In many respects, however, these models are also an ideal vehicle for analyzing ...
متن کاملSome nonlinear exponential smoothing models are unstable
This paper discusses the instability of eleven nonlinear state space models that underly exponential smoothing. Hyndman et al. (2002) proposed a framework of 24 state space models for exponential smoothing, including the well-known simple exponential smoothing, Holt’s linear and Holt-Winters’ additive and multiplicative methods. This was extended to 30 models with Taylor’s (2003) damped multipl...
متن کاملA generalized sequential Bonferroni procedure using smoothed weights for genome-wide association studies incorporating information on Hardy-Weinberg disequilibrium among cases.
BACKGROUND/OBJECTIVES For genome-wide association studies (GWAS) with case-control designs, one of the most widely used association tests is the Cochran-Armitage (CA) trend test assuming an additive mode of inheritance. The CA trend test often has higher power than other association tests under additive and multiplicative disease models. However, it can have very low power under a recessive dis...
متن کاملStochastic Models for Pricing Weather Derivatives using Constant Risk Premium
‎Pricing weather derivatives is becoming increasingly useful‎, ‎especially in developing economies‎. ‎We describe a statistical model based approach for pricing weather derivatives by modeling and forecasting daily average temperatures data which exhibits long-range dependence‎. ‎We pre-process the temperature data by filtering for seasonality and volatility an...
متن کامل