Additive models in high dimensions
نویسندگان
چکیده
منابع مشابه
Additive models in high dimensions
We discuss some aspects of approximating functions on high-dimensional data sets with additive functions or ANOVA decompositions, that is, sums of functions depending on fewer variables each. It is seen that under appropriate smoothness conditions, the errors of the ANOVA decompositions are of order O(n) for indendent predictor variables and approximations using sums of functions of up to m var...
متن کاملEfficient Sampling for Learning Sparse Additive Models in High Dimensions
We consider the problem of learning sparse additive models, i.e., functions of the form: f(x) = ∑ l∈S φl(xl), x ∈ R from point queries of f . Here S is an unknown subset of coordinate variables with |S| = k d. Assuming φl’s to be smooth, we propose a set of points at which to sample f and an efficient randomized algorithm that recovers a uniform approximation to each unknown φl. We provide a ri...
متن کاملLearning Sparse Additive Models with Interactions in High Dimensions
A function f : R → R is referred to as a SparseAdditive Model (SPAM), if it is of the formf(x) =∑l∈S φl(xl), where S ⊂ [d], |S| d.Assuming φl’s and S to be unknown, the prob-lem of estimating f from its samples has beenstudied extensively. In this work, we consider ageneralized SPAM, allowing for second order in-teraction terms. For someS1 ⊂ [d],S2 ⊂<...
متن کاملAlgorithms for Learning Sparse Additive Models with Interactions in High Dimensions
A function f : Rd → R is a sparse additive model (SPAM), if it is of the form f (x) = ∑l∈S φl(xl), where S ⊂ [d], |S | d. Assuming φ’s,S to be unknown, there exists extensive work for estimating f from its samples. In this work, we consider a generalized version of SPAMs that also allows for the presence of a sparse number of second-order interaction terms. For some S1 ⊂ [d],S2 ⊂ ([d] 2 ) , wit...
متن کاملLearning Single Index Models in High Dimensions
Single Index Models (SIMs) are simple yet flexible semi-parametric models for classification and regression. Response variables are modeled as a nonlinear, monotonic function of a linear combination of features. Estimation in this context requires learning both the feature weights, and the nonlinear function. While methods have been described to learn SIMs in the low dimensional regime, a metho...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ANZIAM Journal
سال: 2005
ISSN: 1445-8810
DOI: 10.21914/anziamj.v46i0.1015