Shannon sampling and function reconstruction from point values

Abstract

PreambleI first met René at the well-known 1956 meeting on topology in Mexico City. He then came to the University of Chicago, where I was starting my job as instructor for the fall of 1956. He, Suzanne, Clara and I became good friends and saw much of each other for many decades, especially at IHES in Paris.Thom's encouragement and support were important for me, especially in my first years after my Ph.D. I studied his work in cobordism, singularities of maps, and transversality, gaining many insights. I also enjoyed listening to his provocations, for example his disparaging remarks on complex analysis, 19th century mathematics, and Bourbaki. There was also a stormy side in our relationship. Neither of us could hide the pain that our public conflicts over "catastrophe theory" caused.René Thom was a great mathematician, leaving his impact on a wide part of mathematics. I will always treasure my memories of him.

Learning Theory Estimates via Integral Operators and Their Approximations

“…The bound (3.10) estimates the regularization error [10]. It is only used for the proof of Corollary 3 below.…”

“…To understand (1.3), following our previous studies on Shannon sampling [10,11], we define the sampling operator S x : H K → IR m associated with a discrete subset…”

Learning Rates of Least-Square Regularized Regression

“…The first term in (1.11) is called the regularization error [19]. It can be expressed as a K-functional, since for any measurable function f : X → IR, there holds…”

A signal theory approach to support vector classification: The sinc kernel

“…For a given class of data, we show how to estimate, a priori, a suitable kernel and parameter subspace. Smale and Zhou (2004) have also studied the application of sampling theory and reproducing kernel Hilbert spaces to learning theory. They consider the least squares loss regression problem and construct probability estimates for the sampling error.…”