ICML 2012 workshop: RKHS and Kernel-based methods

ICML 2012 workshop: RKHS and Kernel-based methods: Theoretical topics
and recent advances

Submissions are invited for the workshop to be held on July 1st at
this years’ ICML workshops in Edinburgh.


Research on reproducing kernel Hilbert spaces and kernel-based methods
has witnessed a major impetus during the last two decades. Recent
advances include kernels on structured data, powerful learning
guarantees for kernel-based methods, and Hilbert-space embeddings of
distributions. Moreover, some of the most lively NIPS and ICML
workshops in recent years have dealt with applications where kernel
approaches are popular, most notably multiple kernel learning,
transfer learning, and multitask learning. While kernel-based methods
are well established in the machine learning practice, certain results
in the underlying theory of RKHS remain relatively inaccessible to the
ML community. Moreover, powerful tools for RKHS developed in other
branches of mathematics, for instance in numerical analysis and
probability, are less well known to machine learning researchers.

The proposed workshop represents an opportunity to bring together
researchers in probability theory, mathematicians, and machine
learning researchers working on RKHS methods. The goals of the
workshop are threefold: first, to provide an accessible review and
synthesis of classical results in RKHS theory from the point of view
of functional analysis, probability theory, and numerical analysis.
Second, to cover recent advances in RKHS theory relevant to machine
learners (for instance, operator valued RKHS, kernels on time series,
kernel embeddings of conditional probabilities). Third, to provide a
forum for open problems, to elucidate misconceptions that sometimes
occur in the literature, and to discuss technical challenges.

Confirmed speakers:

Paul Eggermont, University of Delaware
Saburou Saitoh, Gunma University
Robert Schaback, Georg-August-Universitaet Goettingen
Marco Cuturi, University of Kyoto
Lorenzo Rosasco, MIT

Submission scope:

Submissions are invited on new research directions in kernel theory,
and on open questions/striking counterexamples illustrating
non-obvious RKHS properties. We expect the latter to provide a
valuable knowledge base for the ML community in general, of
information known informally to practitioners but not easy to find in
journals articles and conference proceedings.

Accepted submissions will be presented in one of three formats.
Long-form reseach will be presented either as a talk or a poster.

Topics suited to spotlight presentation, such as open questions, interesting
examples, or counterexamples, will be presented during discussion
periods set aside for this purpose.

Long-form submissions accepted as posters will also be considered for
spotlight presentation.

The deadline for submission will be May 20th for the poster and talk
presentations. Notification of acceptance will be provided on June 2.
In addition, proposals for spotlight presentation only will be
accepted until June 15th, with notification on June 17th.

Submissions should be no more than TWO pages in a sane font, and
should be sent to bharath@gatsby.ucl.ac.uk with subject “icml12
workshop submission”.

Current workshop information may be found at:


Further information will be posted on the website.

Your Workshop Organizers,

Arthur Gretton
Zaid Harchaoui
Bharath Sriperumbudur