Special Issue on

Algorithmic Learning Theory

for ALT 2007 in

Theoretical Computer Science

ALT 07 Logo

appeared as:


Theoretical Computer Science, Volume 410, Issue 19, April 28, 2009.

The Special Issue on Algorithmic Learning Theory (ALT 2007) has been edited by Marcus Hutter and Rocco A. Servedio.


Table of Contents

Marcus Hutter and Rocco A. Servedio.
Preface,
pp. 1747-1748
Markus Maier, Matthias Hein, and Ulrike von Luxburg.
Optimal construction of k-nearest-neighbor graphs for identifying noisy clusters,
Abstract.
pp. 1749-1764
Kevin L. Chang.
Multiple pass streaming algorithms for learning mixtures of distributions in Rd,
Abstract.
pp. 1765-1780
Vladimir V. V'yugin.
On calibration error of randomized forecasting algorithms,
Abstract.
pp. 1781-1795
Sanjay Jain, Frank Stephan, and Nan Ye.
Prescribed learning of r.e. classes,
Abstract.
pp. 1796-1806
Ryo Yoshinaka.
Learning efficiency of very simple grammars from positive data,
Abstract.
pp. 1807-1825
M.M. Hassan Mahmud.
On universal transfer learning,
Abstract.
pp. 1826-1846
Kilho Shin and Tetsuji Kuboyama.
Polynomial summaries of positive semidefinite kernels,
Abstract.
pp. 1847-1862
John Case and Samuel E. Moelius III.
Parallelism increases iterative learning power,
Abstract.
pp. 1863-1875
Jean-Yves Audibert, Rémi Munos, and Csaba Szepesvári.
Exploration-exploitation tradeoff using variance estimates in multi-armed bandits,
Abstract.
pp. 1876-1902
Vitaly Feldman and Shrenik Shah.
Separating models of learning with faulty teachers,
Abstract.
pp. 1903-1912
uparrowback to the ALT Archives page

Valid HTML 4.1!