EMMDS 2009. European Workshop on Challenges in Modern Massive Data Sets

Technical University of Denmark
July 1–4, 2009


The 2009 European Workshop on Challenges in Modern Massive Data Sets (EMMDS 2009) will address algorithmic, mathematical, and statistical challenges in modern large-scale data analysis. The goals of EMMDS 2009 are to explore novel techniques for modelling and analyzing massive, high-dimensional, and nonlinearly-structured scientific and internet data sets, and to bring together computer scientists, statisticians, mathematicians, and data analysis practitioners to promote cross-fertilization of ideas. Several areas that will be discussed in detail include:

For information on previous MMDS meetings see http://mmds.stanford.edu.


Click here to download the full program.

Wednesday, July 1, 2009. Theme: Statistical Learning and Machine Learning

Time Talk
09:10 - 10:10 Jerome Friedman
Predictive learning via rule ensembles
10:30 - 11:15 Yee Whye Teh
Bayesian nonparametrics in document and language modeling
11:15 - 12:00 Ole Winther
Hierarchical bayesian modelling for collaborative filtering
13:30 - 14:30 Bernhard Schölkopf
Machine learning with positive definite kernels
14:30 - 15:05 Klaus Mosegaard
Metaheuristics in science and engineering
15:25 - 16:00 Nello Cristianini
Looking for memes in media content
16:00 - 16:35 Mikkel Schmidt
Bayesian matrix factorization approaches to blind source separation

Thursday, July 2, 2009. Theme: Multilinear Algebra for Data Analysis

Time Talk
09:00 - 10:00 Edward Chang
Parallel algorithms for collaborative filtering
10:20 - 10:55 Rasmus Bro
Applications of tensor methods in life sciences data
10:55 - 11:30 Pierre Comon
Tensor decompositions in statistical signal processing
11:30 - 12:05 Lieven De Lathauwer
Tucker compression, Parallel Factor Analysis and block term decompositions: New results
12:05 - 12:40 Lars Eldén
Krylov methods for tensors
14:00 - 15:00 Tomaso Poggio
From neuroscience to hierarchical learning architectures
15:00 - 17:45 Poster Session

Friday, July 3, 2009. Theme: Neuroscience and Clustering

Time Talk
09:00 - 10:00 Ricardo Baeza-Yates
The power of data
10:20 - 11:20 Scott Makeig
Multiscale brain/body imaging: Towards a single brain electrophysiology
11:25 - 12:00 John Ashburner
Brain morphometrics from MRI scans data
13:30 - 14:30 Joachim Buhmann
Structure validation in clustering by stability analysis
14:30 - 15:05 Charles Elkan
Accounting for burstiness in topic models
15:25 - 16:00 Neil Lawrence
Nonlinear matrix factorization with gaussian processes
16:00 - 16:35 Michael Mahoney
Community structure in large social and information networks
16:35 - 17:10 Morten Mørup
Clustering on the simplex

Saturday, July 4, 2009. Theme: New Mathematical Tools for Data Analysis and Social Computing

Time Talk
09:00 - 10:00 Gunnar Carlsson
Topology and data
10:20 - 10:55 Risi Kondor
Non-commutative harmonic analysis in machine learning: the skew spectrum and the graphlet spectrum of graphs
10:55 - 11:30 Samuel Kaski
Probabilistic retrieval and visualization of relevant experiments
11:30 - 12:05 Lek-Heng Lim
Principal cumulant components analysis
13:30 - 14:30 Pedro Cano
Music recommendation systems: A complex networks perspective
14:30 - 15:05 Joaquin Quiñonero Candela
Probabilistic machine learning in computational advertising
15:25 - 16:00 Mark Herbster
Resistive geometry for graph-based transduction
16:00 - 16:35 Sune Lehmann
Connections matter. Communities of links in complex networks
16:35 - 17:10 Lars Kai Hansen
Machine learning in complex networks

Confirmed Speakers

John Ashburner University College London
Ricardo Baeza-Yates Yahoo! Research, Barcelona
Rasmus Bro University of Copenhagen
Joachim Buhmann Swiss Federal Institute of Technology (ETH), Zürich
Joaquin Quiñonero Candela Microsoft Research, Cambridge
Pedro Cano Barcelona Music and Audio Technologies
Edward Chang Google Research, Beijing
Pierre Comon University of Nice, Sophia-Antipolis
Nello Cristianini University of Bristol
Lieven De Lathauwer Katholieke Universiteit Leuven
Lars Elden Linköping University
Charles Elkan University of California, San Diego
Jerome Friedman Stanford University
Mark Herbster University College London
Samuel Kaski Helsinki University of Technology
Risi Kondor University College London / California Institute of Technology
Neil Lawrence University of Manchester
Sune Lehmann Northeastern University / Harvard University
Scott Makeig University of California, San Diego
Klaus Mosegaard University of Copenhagen
Tomaso Poggio Massachusetts Institute of Technology
Mikkel Schmidt University of Cambridge
Bernhard Schölkopf Max Planck Institute
Yee Whye Teh University College London
Ole Winther Technical University of Denmark / University of Copenhagen


Morten Mørup, Technical University of Denmark

Lek-Heng Lim, University of California, Berkeley

Michael Mahoney, Stanford University

Lars Kai Hansen, Technical University of Denmark

Gunnar Carlsson, Stanford University

Contact: mmds-organizers@imm.dtu.dk

Sponsored by

DTU Informatics Graduate School Technical University of Denmark
Center for integrated molecular brain imaging Center for Computational Cognitive Modeling
Danish Sound Technology Network Intelligent Sound