learning theory - gbv
TRANSCRIPT
Nader H. Bshouty Claudio Gentile (Eds.)
Learning Theory
20th Annual Conference on Learning Theory, COLT 2007 San Diego, CA, USA, June 13-15, 2007 Proceedings
4y Spri ringer
Table of Contents
Invited Presentat ions
Property Testing: A Learning Theory Perspective 1 Dana Ron
Spectral Algorithms for Learning and Clustering 3 Santosh S. Vempala
Unsupervised, Semisupervised and Active Learning I
Minimax Bounds for Active Learning 5 Rui M. Castro and Robert D. Nowak
Stability of fc-Means Clustering 20 Shai Ben-David, David Pal, and Hans Ulrich Simon
Margin Based Active Learning 35 Maria-Florina Balcan, Andrei Broder, and Tong Zhang
Unsupervised, Semisupervised and Active Learning II
Learning Large-Alphabet and Analog Circuits with Value Injection Queries 51
Dana Angluin, James Aspnes, Jiang Chen, and Lev Reyzin
Teaching Dimension and the Complexity of Active Learning 66 Steve Hanneke
Multi-view Regression Via Canonical Correlation Analysis 82 Sham M. Kakade and Dean P. Foster
Statistical Learning Theory
Aggregation by Exponential Weighting and Sharp Oracle Inequalities . . . 97 Arnak S. Dalalyan and Alexandre B. Tsybakov
Occam's Hammer 112 Gilles Blanchard and Frangois Fleuret
Resampling-Based Confidence Regions and Multiple Tests for a Correlated Random Vector 127
Sylvain Arlot, Gilles Blanchard, and Etienne Roquain
X Table of Contents
Suboptimality of Penalized Empirical Risk Minimization in Classification 142
Guülaume Lecue
Transductive Rademacher Complexity and Its Applications 157 Ran El-Yaniv and Dmitry Pechyony
Inductive Inference
U-Shaped, Iterative, and Iterative-with-Counter Learning 172 John Case and Samuel E. Moelius III
Mind Change Optimal Learning of Bayes Net Structure 187 Oliver Schulte, Wei Luo, and Russell Greiner
Learning Correction Grammars 203 Lorenzo Cariucci, John Case, and Sanjay Jain
Mitotic Classes 218 Sanjay Jain and Frank Stephan
Online and Reinforcement Learning I
Regret to the Best vs. Regret to the Average 233 Eyal Even-Dar, Michael Kearns, Yishay Mansour, and Jennifer Wortman
Strategies for Prediction Under Imperfect Monitoring 248 Gabor Lugosi, Shie Mannor, and Gilles Stoltz
Bounded Parameter Markov Decision Processes with Average Reward Criterion 263
Ambuj Tewari and Peter L. Bartlett
Online and Reinforcement Learning II
On-Line Estimation with the Multivariate Gaussian Distribution 278 Sanjoy Dasgupta and Daniel Hsu
Generalised Entropy and Asymptotic Complexities of Languages 293 Yuri Kalnishkan, Vladimir Vovk, and Michael V. Vyugin
Q-Learning with Linear Function Approximation 308 Francisco S. Melo and M. Isabel Ribeiro
Regularized Learning, Kernel Methods, SVM
How Good Is a Kernel When Used as a Similarity Measure? 323 Nathan Srebro
Table of Contents X I
Gaps in Support Vector Optimization 336 Nikolas List, Don Hush, Clint Scovel, and Ingo Steinwart
Learning Languages with Rational Kernels 349 Corinna Cortes, Leonid Kontorovich, and Mehryar Mohri
Generalized SMO-Style Decomposition Algorithms 365 Nikolas List
Learning Algorithms and Limitations on Learning
Learning Nested Halfspaces and Uphill Decision Trees 378 Adam, Tauman Kalai
An EfScient Re-scaled Perceptron Algorithm for Conic Systems 393 Alexandre Belloni, Robert M. Freund, and Santosh S. Vempala
A Lower Bound for Agnostically Learning Disjunctions 409 Adam R. Klivans and Alexander A. Sherstov
Sketching Information Divergences 424 Sudipto Guha, Piotr Indyk, and Andrew McGregor
Online and Reinforcement Learning III
Competing with Stationary Prediction Strategies 439 Vladimir Vovk
Improved Rates for the Stochastic Continuum-Armed Bandit Problem 454
Peter Auer, Ronald Ortner, and Csaba Szepesvdri
Learning Permutations with Exponential Weights 469 David P. Helmbold and Manfred K. Warmuth
Online and Reinforcement Learning IV
Multitask Learning with Expert Advice 484 Jacob Abernethy, Peter Bartlett, and Alexander Rakhlin
Online Learning with Prior Knowledge 499 Elad Hazan and Nimrod Megiddo
Dimensionality Reduction
Nonlinear Estimators and Tail Bounds for Dimension Reduction in li Using Cauchy Random Projections 514
Fing Li, Trevor J. Hastie, and Kenneth W. Church
XII Table of Contents
Sparse Density Estimation with i\ Penalties 530 Florentina Bunea, Alexandre B. Tsybakov, and Märten H. Wegkamp
l\ Regularization in Infinite Dimensional Feature Spaces 544 Saharon Rosset, Grzegorz Swirszcz, Nathan Srebro, and Ji Zhu
Prediction by Categorical Features: Generalization Properties and Application to Feature Ranking 559
Sivan Sabato and Shai Shalev-Shwartz
Other Approaches
Observational Learning in Random Networks 574 Julian Lorenz, Martin Marciniszyn, and Angelika Steger
The Loss Rank Principle for Model Selection 589 Marcus Hutter
Robust Reductions from Ranking to Classification 604 Maria-Florina Balcan, Nikhil Bansal, Alina Beygelzimer, Don Coppersmüh, John Langford, and Gregory B. Sorkin
Open Problems
Rademacher Margin Complexity 620 Liwei Wang and Jufu Feng
Open Problems in Efficient Semi-supervised PAC Learning 622 Avrim Blum and Maria-Florina Balcan
Resource-Bounded Information Gathering for Correlation Clustering . . . 625 Pallika Kanani and Andrew McCallum
Are There Local Maxima in the Infinite-Sample Likelihood of Gaussian Mixture Estimation? 628
Nathan Srebro
When Is There a Free Matrix Lunch? 630 Manfred K. Warmuth
Author Index 633