Search Results - "Scovel, Clint"

Mercer’s Theorem on General Domains: On the Interaction between Measures, Kernels, and RKHSs by Steinwart, Ingo, Scovel, Clint

“…Given a compact metric space X and a strictly positive Borel measure ν on X , Mercer’s classical theorem states that the spectral decomposition of a positive…”
Get full text

Separability of reproducing kernel spaces by OWHADI, HOUMAN, SCOVEL, CLINT

“…We demonstrate that a reproducing kernel Hilbert or Banach space of functions on a separable absolute Borel space or an analytic subset of a Polish space is…”
Get full text

Elliptically Contoured Distributions for Anomalous Change Detection in Hyperspectral Imagery by Theiler, James, Scovel, Clint, Wohlberg, Brendt, Foy, Bernard R

“…We derive a class of algorithms for detecting anomalous changes in hyperspectral image pairs by modeling the data with elliptically contoured (EC)…”
Get full text

Fast Rates for Support Vector Machines Using Gaussian Kernels by Steinwart, Ingo, Scovel, Clint

“…For binary classification we establish learning rates up to the order of n⁻¹ for support vector machines (SVMs) with hinge loss and Gaussian RBF kernels. These…”
Get full text

On the Brittleness of Bayesian Inference by Owhadi, Houman, Scovel, Clint, Sullivan, Tim

“…With the advent of high-performance computing, Bayesian methods are becoming increasingly popular tools for the quantification of uncertainty throughout…”
Get full text

Uncertainty quantification of the 4th kind; optimal posterior accuracy-uncertainty tradeoff with the minimum enclosing ball by Bajgiran, Hamed Hamze, Batlle, Pau, Owhadi, Houman, Samir, Mostafa, Scovel, Clint, Shirdel, Mahdy, Stanley, Michael, Tavallali, Peyman

“…Uncertainty quantification (UQ) is, broadly, the task of determining appropriate uncertainties to model predictions. There are essentially three kinds of…”
Get full text

Learning from dependent observations by Steinwart, Ingo, Hush, Don, Scovel, Clint

“…In most papers establishing consistency for learning algorithms it is assumed that the observations used for training are realizations of an i.i.d. process. In…”
Get full text

Brittleness of Bayesian inference under finite information in a continuous world by Owhadi, Houman, Scovel, Clint, Sullivan, Tim

Get full text

An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels by Steinwart, I., Hush, D., Scovel, C.

“…Although Gaussian radial basis function (RBF) kernels are one of the most often used kernels in modern machine learning methods such as support vector machines…”
Get full text

Radial kernels and their reproducing kernel Hilbert spaces by Scovel, Clint, Hush, Don, Steinwart, Ingo, Theiler, James

“…We describe how to use Schoenberg’s theorem for a radial kernel combined with existing bounds on the approximation error functions for Gaussian kernels to…”
Get full text

Polynomial-Time Decomposition Algorithms for Support Vector Machines by Hush, Don, Scovel, Clint

“…This paper studies the convergence properties of a general class of decomposition algorithms for support vector machines (SVMs). We provide a model algorithm…”
Get full text

Stability of unstable learning algorithms by HUSH, Don, SCOVEL, Clint, STEINWART, Ingo

“…We introduce graphical learning algorithms and use them to produce bounds on error deviance for unstable learning algorithms which possess a partial form of…”
Get full text

Concentration of the hypergeometric distribution by Hush, Don, Scovel, Clint

“…In this paper we provide an improved concentration of measure theorem for the hypergeometric distribution…”
Get full text

Universal Scalable Robust Solvers from Computational Information Games and fast eigenspace adapted Multiresolution Analysis by Owhadi, Houman, Scovel, Clint

“…We show how the discovery of robust scalable numerical solvers for arbitrary bounded linear operators can be automated as a Game Theory problem by…”
Get full text

Kernel Mode Decomposition and programmable/interpretable regression networks by Owhadi, Houman, Scovel, Clint, Yoo, Gene Ryan

“…Mode decomposition is a prototypical pattern recognition problem that can be addressed from the (a priori distinct) perspectives of numerical approximation,…”
Get full text

Towards Machine Wald by Owhadi, Houman, Scovel, Clint

“…The past century has seen a steady increase in the need of estimating and predicting complex systems and making (possibly critical) decisions with limited…”
Get full text

Separability of reproducing kernel spaces by Owhadi, Houman, Scovel, Clint

“…We demonstrate that a reproducing kernel Hilbert or Banach space of functions on a separable absolute Borel space or an analytic subset of a Polish space is…”
Get full text

Conditioning Gaussian measure on Hilbert space by Owhadi, Houman, Scovel, Clint

“…For a Gaussian measure on a separable Hilbert space with covariance operator $C$, we show that the family of conditional measures associated with conditioning…”
Get full text

Extreme points of a ball about a measure with finite support by Owhadi, Houman, Scovel, Clint

“…We show that, for the space of Borel probability measures on a Borel subset of a Polish metric space, the extreme points of the Prokhorov, Monge-Wasserstein…”
Get full text

Qualitative Robustness in Bayesian Inference by Owhadi, Houman, Scovel, Clint

“…The practical implementation of Bayesian inference requires numerical approximation when closed-form expressions are not available. What types of accuracy…”
Get full text