ALT 2011

34 papers

Accelerated Training of Max-Margin Markov Networks with Kernels Xinhua Zhang, Ankan Saha, S. V. N. Vishwanathan

Adaptive and Optimal Online Linear Regression on ℓ1-Balls Sébastien Gerchinovitz, Jia Yuan Yu

Approximate Reduction from AUC Maximization to 1-Norm Soft Margin Optimization Daiki Suehiro, Kohei Hatano, Eiji Takimoto

Asymptotically Optimal Agents Tor Lattimore, Marcus Hutter

Axioms for Rational Reinforcement Learning Peter Sunehag, Marcus Hutter

Combining Initial Segments of Lists Manfred K. Warmuth, Wouter M. Koolen, David P. Helmbold

Competing Against the Best Nearest Neighbor Filter in Regression Arnak S. Dalalyan, Joseph Salmon

Deviations of Stochastic Bandit Regret Antoine Salomon, Jean-Yves Audibert

Distributional Learning of Simple Context-Free Tree Grammars Anna Kasprzik, Ryo Yoshinaka

Domain Adaptation in Regression Corinna Cortes, Mehryar Mohri

Erratum: Learning Without Coding Samuel E. Moelius, Sandra Zilles

Information Distance and Its Extensions Ming Li

Iterative Learning from Positive Data and Counters Timo Kötzing

Learning a Classifier When the Labeling Is Known Shalev Ben-David, Shai Ben-David

Learning and Classifying Sanjay Jain, Eric Martin, Frank Stephan

Learning from Label Preferences Eyke Hüllermeier, Johannes Fürnkranz

Learning Relational Patterns Michael Geilke, Sandra Zilles

Lipschitz Bandits Without the Lipschitz Constant Sébastien Bubeck, Gilles Stoltz, Jia Yuan Yu

Making Online Decisions with Bounded Memory Chi-Jen Lu, Wei-Fu Lu

Models for Autonomously Motivated Exploration in Reinforcement Learning - (Extended Abstract) Peter Auer, Shiau Hong Lim, Chris Watkins

On Noise-Tolerant Learning of Sparse Parities and Related Problems Elena Grigorescu, Lev Reyzin, Santosh S. Vempala

On the Expressive Power of Deep Architectures Yoshua Bengio, Olivier Delalleau

On Upper-Confidence Bound Policies for Switching Bandit Problems Aurélien Garivier, Eric Moulines

Optimal Estimation Jorma Rissanen

Re-Adapting the Regularization of Weights for Non-Stationary Regression Nina Vaits, Koby Crammer

Regret Minimization Algorithms for Pricing Lookback Options Eyal Gofer, Yishay Mansour

Robust Learning of Automatic Classes of Languages Sanjay Jain, Eric Martin, Frank Stephan

Semantic Communication for Simple Goals Is Equivalent to On-Line Learning Brendan Juba, Santosh S. Vempala

Supervised Learning and Co-Training Malte Darnstädt, Hans Ulrich Simon, Balázs Szörényi

The Perceptron with Dynamic Margin Constantinos Panagiotakopoulos, Petroula Tsampouka

Time Consistent Discounting Tor Lattimore, Marcus Hutter

Universal Knowledge-Seeking Agents Laurent Orseau

Universal Prediction of Selected Bits Tor Lattimore, Marcus Hutter, Vaibhav Gavane

Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits Alexandra Carpentier, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Peter Auer