The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
Activity Number:
|
510
|
Type:
|
Contributed
|
Date/Time:
|
Wednesday, August 3, 2011 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract - #302432 |
Title:
|
Minimax-Optimal Rates for Sparse Additive Models Over Kernel Classes via Convex Programming
|
Author(s):
|
Garvesh Raskutti*+
|
Companies:
|
University of California at Berkeley
|
Address:
|
, , ,
|
Keywords:
|
high-dimensional ;
sparse additive models ;
minimax ;
convex optimization
|
Abstract:
|
Sparse additive models are families of $d$-variate functions that have the additive decomposition \mbox{$f^* = \sum_{j \in S} f^*_j$,} where $S$ is a unknown subset of cardinality $s \ll d$. We consider the case where each component function $f^*_j$ lies in a reproducing kernel Hilbert space, and analyze a simple kernel-based convex program for estimating the unknown function $f^*$. Working within a high-dimensional framework that allows both the dimension $d$ and sparsity $s$ to scale, we derive convergence rates in the $L^2(\mathbb{P})$ and $L^2(\mathbb{P}_n)$ norms. These rates consist of two terms: a \emph{subset selection term} of the order $\frac{s \log d}{n}$, corresponding to the difficulty of finding the unknown $s$-sized subset, and an \emph{estimation error} term of the order $s \, \nu_n^2$, where $\nu_n^2$ is the optimal rate for estimating an univariate function within the RKHS. We complement these achievable results by deriving minimax lower bounds on the $L^2(\mathbb{P})$ error, thereby showing that our method is optimal up to constant factors for sub-linear sparsity $s = o(d)$. Thus, we obtain optimal minimax rates for classes of sparse additive models.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.