SRC Logo

Machine Learning, Statistics, and Discovery

Sunday, June 22 - Thursday, June 26, 2003

Organizers:

Joseph S. Verducci, Ohio State University
Xiaotong Shen, Ohio State University
 John Lafferty,Carnegie Mellon University

Machine learning is an active and rapidly growing area of research that offers systematic and machine-implementable approaches to extracting information from vast and complex data sources. The goal of this conference was to assemble researchers from the disciplines of computer science and statistics around the topical themes of support vector machines and other large margin classifiers, boosting and ensemble methods, new extensions of classification and regression, methods for approximate inference, and application areas. The conference resulted in a lively exchange between the two communities, which will hopefully lead to cross-fertilization and new collaborations across traditional academic disciplines.

The conference schedule and links to the slides for the presentations are given below.

Web site for the 2003 AMS-IMS-SIAM Summer Research Conferences.
Web site for the 2006 Conference

 
Day 1: Sunday, June 22
Time Speaker Title
9:30 Joe Verducci Welcome
9:14 Leo Breiman The Evolution of Statistics, Machine Learning, and Data Mining
10:30 Break
11:00 Tomaso Poggio Statistical Learning Theory: Some New Results and Applications [pdf of paper]
12:15 Lunch
1:30 Steve Ellis Instability in Learning [postscript]
2:30 Shaojun Wang The Latent Maximum Entropy Principle [postscript]
3:30 Break
4:00 Discussion  
     
Day 2: Monday, June 23
Time Speaker Title
8:30 Tommi Jaakkola Regularization and Partially Labeled Data [pdf]
9:30 Hugo Zaragoza A Statistical Analysis of Ranking Measures [powerpoint, postscript]
10:30 Break
11:00 John Lafferty Graph Kernels and Random Fields for Semi-Supervised Learning [pdf]
12:15 Lunch
1:30 Rob Schapire Recent Work on Boosting [postscript]
2:30 Yongdai Kim Boosting on the Convex Hull [pdf]
3:30 Break
4:00 David Heckerman Staged Mixture Modeling and Boosting [powerpoint, pdf of paper]
5:00 Discussion  
     
Day 3: Tuesday, June 24
Time Speaker Title
8:30 Xiaotong Shen Psi Learning [pdf]
9:30 Yi Lin Statistical Properties of the Support Vector Machine and Related Topics [pdf]
10:30 Break
11:00 Peter Bartlett Convexity, Classification, and Risk Bounds [postscript]
12:15 Lunch
1:30 Marina Meila Comparing Clusterings by Variation of Information [pdf (talk), pdf (paper)]
2:30 Jia Li Classification of High Dimensional Data by Two-Way Mixture Models [pdf]
3:30 Break
4:00 Yoram Singer Learning Algorithms for Enclosing Points in Bregmanian Spheres
4:45 Discussion  
     
Day 4: Wednesday, June 25
Time Speaker Title
8:30 Joe Verducci Learning Issues in Drug Discovery [powerpoint]
9:30 Stan Young High Throughput Target Investigation: Guilt by Association [powerpoint]
10:30 Break
11:00 Art Owen A Gene Recommender for C. elegans [pdf]
12:15 Lunch and afternoon off
7:00 John Moody Learning to Trade via Direct Reinforcement [pdf]
8:00 Mike Larsen Hierarchical Bayesian Linkage and Regression in Linked Files [pdf]
3:30 Break
9:00 Discussion  
     
Day 5: Thursday, June 26
Time Speaker Title
8:30 Leo Breiman RF: A Two-Eyed Algorithm for Both Supervised and Unsupervised Data [pdf]
9:30 Steve Marron Distance Weighted Discrimination and Geometrical Representation [pdf]
10:30 Break
11:00 Tony Jebara Kernels Between Distributions and Sets [pdf]
12:15 Lunch
1:30 George Michailidis Application of Rule-Based Methods to Class Prediction Problems [postscript]
2:15 Yufeng Liu Multi-category Psi-Learning and Support Vector Machines [postscript]
3:00 Break
3:30 Helen Zhang Variable Selection Support Vector Machines [pdf]
4:15 Adele Cutler Graphical Tools for Random Forests