267 citations · 813 across the 34 of their papers we have counts for
9 papers · 1 filter
Intrinsic Dimension Adaptive Partitioning for Kernel Methods
Thomas Hamm, Ingo Steinwart
We prove minimax optimal learning rates for kernel ridge regression, resp.~support vector machines based on a data dependent partition of the input space, where the dependence of t…
Adaptive Learning Rates for Support Vector Machines Working on Data with Low Intrinsic Dimension
Thomas Hamm, Ingo Steinwart
We derive improved regression and classification rates for support vector machines using Gaussian kernels under the assumption that the data has some low-dimensional intrinsic stru…
PAC-Bayesian Bounds for Deep Gaussian Processes
Roman Föll, Ingo Steinwart
Variational approximation techniques and inference for stochastic models in machine learning has gained much attention the last years. Especially in the case of Gaussian Processes…
Improved Classification Rates for Localized SVMs
Ingrid Blaschzyk, Ingo Steinwart
Localized support vector machines solve SVMs on many spatially defined small chunks and one of their main characteristics besides the computational benefit compared to global SVMs…
Improved Classification Rates under Refined Margin Conditions
Ingrid Blaschzyk, Ingo Steinwart
In this paper we present a simple partitioning based technique to refine the statistical analysis of classification algorithms. The core of our idea is to divide the input space in…
Estimating conditional quantiles with the help of the pinball loss
Ingo Steinwart, Andreas Christmann
The so-called pinball loss for estimating conditional quantiles is a well-known tool in both statistics and machine learning. So far, however, only little work has been done to qua…
Consistency and robustness of kernel-based regression in convex risk minimization
Andreas Christmann, Ingo Steinwart
We investigate statistical properties for a broad class of modern kernel-based regression (KBR) methods. These kernel methods were developed during the last decade and are inspired…
Fast rates for support vector machines using Gaussian kernels
Ingo Steinwart, Clint Scovel
For binary classification we establish learning rates up to the order of for support vector machines (SVMs) with hinge loss and Gaussian RBF kernels. These rates are in te…
A new concentration result for regularized risk minimizers
Ingo Steinwart, Don Hush, Clint Scovel
We establish a new concentration result for regularized risk minimizers which is similar to an oracle inequality. Applying this inequality to regularized least squares minimizers l…