NIPS 2002 Workshop
Spectral Methods in Dimensionality Reduction, Clustering, and Classification

Basic information

Date: Friday or Saturday, Dec. 13 or 14, 2002
Length: One day
Location: Whistler, British Columbia, Canada
Contact: Sam Roweis or Josh Tenenbaum


Data-driven learning in neural or artificial systems has often been disparaged as a painfully slow process fraught with local minima. However, by formulating a learning task as an appropriate algebraic problem, globally optimal solutions may be computed efficiently in closed form via an eigendecomposition. Traditionally, this spectral approach was thought to be applicable only to learning problems with an essentially linear structure, such as principal component analysis or linear discriminant analysis. Recently, researchers in machine learning, statistics, and theoretical computer science have figured out how to cast a number of important nonlinear learning problems in terms amenable to spectral methods. These problems include nonlinear dimensionality reduction, nonparameteric clustering, and nonlinear classification with fully or partially labeled data. Spectral approaches to these problems offer the potential for dramatic improvements in efficiency and accuracy relative to traditional iterative or greedy algorithms. Furthermore, numerical methods for spectral computations are extremely mature and well understood, allowing learning algorithms to benefit from a long history of implementation efficiencies in other fields.

The goal of this workshop is to bring together researchers working on spectral approaches across this broad range of problem areas, for a series of talks on state-of-the-art research and discussions of common themes and open questions. Some examples of questions we hope to discuss include:

The workshop will last one day. Most of the talks will be invited, but we welcome contributions for short talks by other researchers. Please contact the organizers if you are interested.

Prospective Participants

Serge Belongie
Mikhail Belkin
Matt Brand
David Donoho
Brendan Frey
Carrie Grimes
Tommi Jaakkola
Risi Kondor
John Lafferty
Marina Meila
Andrew Ng
Partha Niyogi
Sam Roweis
Lawrence Saul
Jianbo Shi
Vin de Silva
Alex Smola
Martin Szummer
Josh Tenenbaum
Yee Why Teh