COLT '96 CONFERENCE SCHEDULE

Note: All talks will take place in the Palazzo del Turismo, Piazza Malvezzi.


Thursday Evening

6:00 - 8:00 Reception and pre-registration in Chiostro Santa Maria de Senioribus, Via Anelli.

Friday Morning

8:30 onward Registration
9:00 - 9:10 Opening of the Conference
Session 1
Chair: Avrim Blum
9:10 - 9:30 Analysis of a Simple Learning Algorithm: Learning Foraging Thresholds for Lizards
Leslie Ann Goldberg, William E. Hart, David Wilson
9:30 - 9:50 VC Dimension of an Integrate and Fire Neuron Model
Anthony M. Zador, Barak A. Pearlmutter
9:50 - 10:10 Graph Learning with a Nearest Neighbor Approach
Sven Koenig, Yury Smirnov
10:10 - 10:30 The Dual DFA problem: Hardness Results for Programming by Demonstration and Learning First-order Representations
William W. Cohen
10:30 - 11:00 Coffee Break
Session 2
Chair: Michael Kearns
11:00 - 11:20 PAC-like Upper Bounds for the Sample Complexity of Leave-One-Out Cross-Validation
Sean B. Holden
11:20 - 11:40 A Data-dependent Skeleton Estimate for Learning
Gabor Lugosi, Marta Pinter
11:40 - 12:00 Towards Robust Model Selection using Estimation and Approximation Error Bounds
Joel Ratsaby, R. Meir, V. Maiorov
12:00 - 12:20 A Framework for Structural Risk Minimisation
John Shawe-Taylor, Peter Bartlett, Robert Williamson, Martin Anthony
12:20 - 2:00 Lunch Break

Friday Afternoon

2:00 - 3:00 Invited Talk by Thomas G. Dietterich (Title to be Announced)
3:00 - 3:30 Coffee Break
Session 3
Chair: Yishay Mansour
3:30 - 3:50 A Bayesian/Information Theoretic Model of Bias Learning
Jonathan Baxter
3:50 - 4:10 Predicting Bits Almost as Well as the Optimal Biased Coin
Yoav Freund
4:10 - 4:30 A Randomized Approximation of the MDL for Stochastic Models with Hidden Variables
Kenji Yamanishi
4:30 - 4:50 Learning an Optimal Decision Strategy in an Influence Diagram with Latent Variables
V.G. Vovk

Friday Evening

7:00 - 8:00 Business Meeting

Saturday Morning

Session 4
Chair: Dana Ron
9:00 - 9:20 On the Complexity of Learning from Drifting Distributions
Rakesh D. Barve, Philip M. Long
9:20 - 9:40 Learning Changing Concepts by Exploiting the Structure of Change
Peter Bartlett, Shai Ben-David, Sanjeev Kulkarni
9:40 - 10:00 The Importance of Convexity in Learning with Squared Loss
Wee SunLee, Peter L. Bartlett, Robert C. Williamson
10:00 - 10:20 Learning Curve Bounds for Markov Decision Processes with Undiscounted Rewards
Lawrence K. Saul, Satinder P. Singh
10:20 - 10:50 Coffee Break
Session 5
Chair: Sanjay Jain
10:50 - 11:10 Probabilistic PFIN-type Learning: General Properties
Andris Ambainis
11:10 - 11:30 Synthesizing Enumeration Techniques For Language Learning
Ganesh Baliga, John Case, Sanjay Jain
11:30 - 11:50 Elementary Formal Systems, Intrinsic Complexity, and Procrastination
Sanjay Jain, Arun Sharma
11:50 - 12:10 Angluin's Theorem for Indexed Families of r.e. Sets and Applications
Dick de Jongh, Makoto Kanazawa

Sunday Morning

Session 6
Chair: Lisa Hellerstein
9:00 - 9:20 On Restricted-Focus-of-Attention Learnability of Boolean Functions
Andreas Birkendorf, Eli Dichterman, Jeffrey Jackson, Norbert Klasner, Hans Ulrich Simon
9:20 - 9:40 Analysis of Greedy Expert Hiring and an Application to Memory-Based Learning
Igal Galperin
9:40 - 10:00 On Learning Width-Two Branching Programs
Nader H. Bshouty, Christino Tamon, David K. Wilson
10:00 - 10:20 PAC Learning Axis-aligned Rectangles with Respect to Product Distributions from Multiple-instance Examples
Philip M. Long, Lei Tan
10:20 - 10:50 Coffee Break
Session 7
Chair: Rob Holte
10:50 - 11:10 Attribute-efficient Learning in Query and Mistake-Bound Models
Nader Bshouty, Lisa Hellerstein
11:10 - 11:30 PAC Learning Intersections of Halfspaces with Membership Queries
Stephen Kwek, Leonard Pitt
11:30 - 11:50 Learning Conjunctions of Two Unate DNF Formulas: Computational and Informational Results
Aaron Feigelson, Lisa Hellerstein
11:50 - 12:10 A Simple Algorithm for Learning O(log n)-Term DNF
Eyal Kushilevitz
12:10 - 2:00 Lunch Break

Sunday Afternoon

2:00 - 3:00 Invited talk by David D. Lewis, "Challenges in Machine Learning for Text Classification"
3:00 - 3:30 Coffee Break
3:30 - 5:00 Impromptu Sesssion I
5:00 - 7:00 Meet the Authors/Posters (with refreshments)

Sunday Evening

7:30 onwards Banquet

Monday Morning

Session 8
Chair: Martin Anthony
9:00 - 9:20 Trees and Learning
Wolfgang Merkle, Frank Stephan
9:20 - 9:40 Learning Branches and Learning to Win Closed Games
Martin Kummer, Matthias Ott
9:40 - 10:00 A Competitive Approach to Game Learning
Christopher D. Rosin, Richard K. Belew
10:00 - 10:20 Strong Minimax Lower Bounds for Learning
Andras Antos, Gabor Lugosi
10:20 - 10:50 Coffee Break
Session 9
Chair: Nick Littlestone
10:50 - 11:10 On-line Portfolio Selection
Erik Ordentlich, Thomas M. Cover
11:10 - 11:30 On Bayes Methods for On-line Boolean Prediction
Nicolò Cesa-Bianchi, David Helmbold, Sandra Panizza
11:30 - 11:50 Game Theory, On-line Prediction and Boosting
Yoav Freund, Robert E. Schapire
11:50 - 12:10 Learning of Depth two Neural Nets with Constant Fan-in at the Hidden Nodes
Peter Auer, Stephen Kwek, Wolfgang Maass, Manfred Warmuth
12:10 - 2:00 Lunch Break

Monday Afternoon

2:00 onwards Impromptu Session II
END OF CONFERENCE

For information, coltinfo@dsi.unimi.it
To the COLT '96 home page.