MMDS. Workshop on Algorithms for Modern Massive Data Sets

The Workshops on Algorithms for Modern Massive Data Sets (MMDS) will address algorithmic, mathematical, and statistical challenges in modern large-scale data analysis. The goals of this series of workshops are to explore novel techniques for modeling 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.

News

Watch out for:

MMDS 2010. Workshop on Algorithms for Modern Massive Data Sets
Stanford University
June 15–18, 2010
Organizing Committee: Michael Mahoney (chair), Lek-Heng Lim, Alex Shkolnik, Petros Drineas, Gunnar Carlsson

MMDS 2006

• 2006 Workshop on Algorithms in Modern Massive Data Sets, Stanford University Stanford, CA, June 21–24, 2006.

• Report: SIAM News article about MMDS 2006.

MMDS 2008

• 2008 Workshop on Algorithms in Modern Massive Data Sets, Stanford University Stanford, CA, June 25–28, 2008.

• Reports: Association for Computing Machinery: ACM KDD Explorations (link). See also the following. American Statistical Association: AMSTAT News (link), Statistical Computing and Statistical Graphics (link); Institute of Mathematical Statistics: IMS Bulletin (link); Society for Industrial and Applied Mathematics: SIAM News Part I (link), SIAM News Part II (link).

• Program:

Wednesday, June 25, 2008. Theme: Data Analysis and Data Applications

Time	Talk
10:00 - 11:00	Tutorial: Christos Faloutsos Graph mining: laws, generators and tools
11:00 - 11:30	Deepak Agarwal Predictive discrete latent models for large incomplete dyadic data
11:30 - 12:00	Chandrika Kamath Scientific data mining: why is it difficult?
2:00 - 3:00	Tutorial: Edward Chang Challenges in mining large-scale social networks
3:00 - 3:30	Sharad Goel Predictive indexing for fast search
3:30 - 4:00	James Demmel Avoiding communication in linear algebra algorithms
4:30 - 5:00	Jun Liu Bayesian inference of interactions and associations
5:00 - 5:30	Fan Chung Four graph partitioning algorithms
5:30 - 6:00	Ronald Coifman Diffusion geometries and harmonic analysis on data sets

Thursday, June 26, 2008. Theme: Networked Data and Algorithmic Tools

Time	Talk
9:00 - 10:00	Tutorial: Milena Mihail Models and algorithms for complex networks, with network elements maintaining characteristic profiles
10:00 - 10:30	Reid Andersen An algorithm for improving graph partitions
11:00 - 11:30	Michael W. Mahoney Community structure in large social and information networks
11:30 - 12:00	Nikhil Srivastava and Daniel Spielman Graph sparsification by effective resistances
12:00 - 12:30	Amin Saberi Sequential algorithms for generating random graphs
2:00 - 3:00	Tutorial: Pankaj K. Agarwal Modeling and analyzing massive terrain data sets
3:00 - 3:30	Leonidas Guibas Detection of symmetries and repeated patterns in 3D point cloud data
3:30 - 4:00	Yuan Yao Topological methods for exploring pathway analysis in complex biomolecular folding
4:30 - 5:00	Piotr Indyk Sparse recovery using sparse random matrices
5:00 - 5:30	Ping Li Algorithms for matrix column selection
5:30 - 6:00	Joel Tropp Compressed counting and stable random projections

Friday, June 27, 2008. Theme: Statistical, Geometric, and Topological Methods

Time	Talk
9:00 - 10:00	Tutorial: Jerome H. Friedman Fast sparse regression and classification
10:00 - 10:30	Tong Zhang An adaptive forward/backward greedy algorithm for learning sparse representations
11:00 - 11:30	Jitendra Malik Classification using intersection kernel SVMs is efficient
11:30 - 12:00	Elad Hazan Efficient online routing with limited feedback and optimization in the dark
12:00 - 12:30	T.S. Jayram Cascaded aggregates on data streams
2:30 - 3:30	Tutorial: Gunnar Carlsson Topology and data
3:30 - 4:00	Partha Niyogi Manifold regularization and semi-supervised learning
4:30 - 5:00	Sanjoy Dasgupta Random projection trees and low dimensional manifolds
5:00 - 5:30	Kenneth Clarkson Tighter bounds for random projections of manifolds
5:30 - 6:00	Yoram Singer Efficient projection algorithms for learning sparse representations from high dimensional data
6:00 - 6:30	Arindam Banerjee Bayesian co-clustering for dyadic data analysis

Saturday, June 28, 2008. Theme: Machine Learning and Dimensionality Reduction

Time	Talk
9:00 - 10:00	Tutorial: Michael I. Jordan Sufficient dimension reduction
10:00 - 10:30	Nathan Srebro More data less work: SVM training in time decreasing with larger data sets
11:00 - 11:30	Inderjit S. Dhillon Rank minimization via online learning
11:30 - 12:00	Nir Ailon Efficient dimension reduction
2:30 - 3:00	Ravi Kannan Spectral algorithms
3:00 - 3:30	Chris Wiggins Inferring and encoding graph partitions
3:30 - 4:00	Anna Gilbert Combinatorial group testing in signal recovery
4:30 - 5:00	Lars Kai Hansen Generalization in high-dimensional matrix factorization
5:00 - 5:30	Holly Jin Exploring sparse nonnegative matrix factorization
5:30 - 6:00	Elizabeth Purdom Data analysis with graphs
6:00 - 6:30	Lek-Heng Lim Ranking via Hodge decompositions of graphs and skew-symmetric matrices

Organizers

• MMDS 2008
• Michael Mahoney, Stanford University
• Lek-Heng Lim, University of California, Berkeley
• Petros Drineas, Rensselaer Polytechnic Institute
• Gunnar Carlsson, Stanford University
• MMDS 2006
• Gene Golub, Stanford University
• Michael Mahoney, Yahoo! Research
• Petros Drineas, Rensselaer Polytechnic Institute
• Lek-Heng Lim, Stanford University

Other MMDS meetings

EMMDS 2009. European Workshop on Challenges in Modern Massive Data Sets, Technical University of Denmark, Lyngby, Denmark, July 1–4, 2009.

MMDS 2008 Speakers