10. COLT 1997: Nashville, Tennessee, USA

Invited Talk I

• Andrew R. Barron: Information Theory in Probability, Statistics, Learning, and Neural Nets (Abstract). 1

Session 1

• John Shawe-Taylor, Robert C. Williamson:
  A PAC Analysis of a Bayesian Estimator. 2-9
  
• Tamás Horváth, Robert H. Sloan, György Turán:
  Learning Logic Programs by Using the Product Homomorphism Method. 10-20
  

Session 2

• Philip M. Long:
  On-line Evaluation and Prediction using Linear Functions. 21-31
  
• V. G. Vovk:
  Derandomizing Stochastic Prediction Strategies. 32-44
  
• Avrim Blum, Carl Burch:
  On-line Learning and the Metrical Task System Problem. 45-53
  

Session 3

• Wolfgang Maass, Michael Schmitt:
  On the Complexity of Learning for a Spiking Neuron (Extended Abstract). 54-61
  
• Tom Bylander:
  Learning Probabilistically Consistent Linear Threshold Functions. 62-71
  
• Claude-Nicolas Fiechter:
  PAC Adaptive Control of Linear Systems. 72-80
  

Session 4

• Robert P. Daley, Bala Kalyanasundaram:
  FINite Learning Capabilities and Their Limits. 81-89
  
• Kalvis Apsitis, Rusins Freivalds, Carl H. Smith:
  Asymmetric Team Learning. 90-95
  
• Arun Sharma, Frank Stephan, Yuri Ventsov:
  Generalized Notions of Mind Change Complexity. 96-108
  

Invited Talk II

• David Haussler:
  A Brief Look at Some Machine Learning Problems in Genomics. 109-113
  

Session 5

• Fernando C. N. Pereira, Yoram Singer:
  An Efficient Extension to Mixture Techniques for Prediction and Decision Trees. 114-121
  
• Ron Meir:
  Performance Bounds for Nonlinear Time Series Prediction. 122-129
  

Session 6

• Scott E. Decatur, Oded Goldreich, Dana Ron:
  Computational Sample Complexity. 130-142
  
• A. Kowalczyk:
  Dense Shattering and Teaching Dimensions for Differentiable Families (Extended Abstract). 143-151
  
• Michael J. Kearns, Dana Ron:
  Algorithmic Stability and Sanity-Check Bounds for Leave-one-Out Cross-Validation. 152-162
  

Session 7

• Nicolò Cesa-Bianchi:
  Analysis of Two Gradient-based Algorithms for On-line Regression. 163-170
  
• Adam J. Grove, Nick Littlestone, Dale Schuurmans:
  General Convergence Results for Linear Discriminant Updates. 171-183
  
• Tom Bylander:
  The Binary Exponentiated Gradient Algorithm for Learning Linear Functions. 184-192
  

Session 8

• Víctor Dalmau:
  A Dichotomy Theorem for Learning Quantified Boolean Formulas. 193-200
  
• Yishay Mansour, Mariano Schain:
  Learning with Maximum-Entropy Distributions. 201-210
  
• Nina Mishra, Leonard Pitt:
  Generating all Maximal Independent Sets of Bounded-Degree Hypergraphs. 211-217
  

Session 9

• David P. Helmbold, Sandra Panizza:
  Some Label Efficient Learning Results. 218-230
  
• Sally A. Goldman, Stephen Kwek, Stephen D. Scott:
  Learning from Examples with Unspecified Attribute Values (Extended Abstract). 231-242
  
• Funda Ergün, Ravi Kumar, Ronitt Rubinfeld:
  Learning Distributions from Random Walks. 243-249
  
• Kenji Yamanishi:
  Distributed Cooperative Bayesian Learning Strategies. 250-262
  

Session 10

• Susanne Kaufmann, Frank Stephan:
  Resource Bounded Next Value and Explanatory Identification: Learning Automata, Patterns and Polynomials On-Line. 263-274
  
• William I. Gasarch, Andrew C. Y. Lee:
  Inferring Answers to Queries. 275-284
  
• Dana Angluin, Martins Krikis:
  Teachers, Learners and Black Boxes. 285-297
  

Joint Sessions with ICML

• Dana Angluin, Miklós Csürös:
  Learning Markov Chains with Variable Memory Length from Noisy Output. 298-308
  
• Avrim Blum, Adam Kalai:
  Universal Portfolios With and Without Transaction Costs. 309-313
  
• Dimitris Bertsimas, David Gamarnik, John N. Tsitsiklis:
  Estimation of Time-Varying Parameters in Statistical Models: An Optimization Approach. 314-324
  
• Sally A. Goldman, Stephen Kwek, Stephen D. Scott:
  Agnostic Learning of Geometric Patterns (Extended Abstract). 325-333
  

Tutorials