Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Learning Multiple Tasks with Kernel Methods

- T. Evgeniou, C. Micchelli, M. Pontil
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 1 December 2005

We study the problem of learning many related tasks simultaneously using kernel methods and regularization. The standard single-task kernel methods, such as support vector machines and regularization… Expand

On Learning Vector-Valued Functions

- C. Micchelli, M. Pontil
- Computer Science, Mathematics
- Neural Computation
- 2005

In this letter, we provide a study of learning in a Hilbert space of vector-valued functions. We motivate the need for extending learning theory of scalar-valued functions by practical considerations… Expand

Learning the Kernel Function via Regularization

- C. Micchelli, M. Pontil
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 1 December 2005

We study the problem of finding an optimal kernel from a prescribed convex set of kernels K for learning a real-valued function by regularization. We establish for a wide variety of regularization… Expand

Interpolation of scattered data: Distance matrices and conditionally positive definite functions

- C. Micchelli
- Mathematics
- 1 December 1986

Among other things, we prove that multiquadric surface interpolation is always solvable, thereby settling a conjecture of R. Franke.

A Survey of Optimal Recovery

- C. Micchelli, T. J. Rivlin
- Computer Science
- 1977

The problem of optimal recovery is that of approximating as effectively as possible a given map of any function known to belong to a certain class from limited, and possibly error-contaminated,… Expand

Using the Refinement Equations for the Construction of Pre-Wavelets II: Powers of Two

- R. Jia, C. Micchelli
- Mathematics, Computer Science
- Curves and Surfaces
- 1 August 1991

We study basic questions of wavelet decompositions associated with multiresolution analysis. A rather complete analysis of multiresolution associated with the solution of a refinement equation is… Expand

Approximation by superposition of a sigmoidal function

- H. Mhaskar, C. Micchelli
- Computer Science
- 1992

- 424
- 18

Universal Kernels

- C. Micchelli, Y. Xu, H. Zhang
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 1 December 2006

In this paper we investigate conditions on the features of a continuous kernel so that it may approximate an arbitrary continuous target function uniformly on any compact subset of the input space. A… Expand

A Spectral Regularization Framework for Multi-Task Structure Learning

- A. Argyriou, C. Micchelli, M. Pontil, Yiming Ying
- Computer Science
- NIPS
- 3 December 2007

Learning the common structure shared by a set of supervised tasks is an important practical and theoretical problem. Knowledge of this structure may lead to better generalization performance on the… Expand