The Special Issue on

Algorithmic Learning Theory

for ALT 2012 in

Theoretical Computer Science

ALT 12 Logo

appeared in

Theoretical Computer Science, Volume 558, November 13, 2014.

The Special Issue on Algorithmic Learning Theory has been edited by Nader H. Bshouty, Gilles Stoltz, Nicolas Vayatis, and Thomas Zeugmann.

Table of Contents

Nader H. Bshouty, Gilles Stoltz, Nicolas Vayatis, and Thomas Zeugmann
Guest Editors' Foreword,

pp. 1–4

Ziyuan Gao, and Frank Stephan
Confident and consistent partial learning of recursive functions ,

pp. 5–17

Christophe Costa Florêncio, and Sicco Verwer,
Regular inference as vertex coloring,
pp. 18–34

Rahim Samei, Pavel Semukhin, Boting Yang, and Sandra Zilles.
Algebraic methods proving Sauer's bound for teaching complexity,
pp. 35–50

Shalev Ben-David, and Lev Reyzin,
Data stability in clustering: A closer look,
pp. 51–61

Ronald Ortner, Daniil Ryabko, Peter Auer, and Rémi Munos.
Regret bounds for restless Markov bandits,
pp. 62–76

Alexandra Carpentier and Rémi Munos.
Minimax number of strata for online stratified sampling: The case of noisy samples,
pp. 77–106

Edward Moroshko and Koby Crammer.
Weighted last-step min-max algorithm with improved sub-logarithmic regret,
pp. 107–124

Tor Lattimore and Marcus Hutter
Near-optimal PAC bounds for discounted MDPs,
pp. 125–143

Wouter M. Koolen and Vladimir Vovk.
Buy low, sell high,
pp. 144–158

Manfred K. Warmuth, Wojciech Kotłowski, and Shuisheng Zhou.
Kernelization of matrix updates, when and how?,
pp. 159–178

uparrowback to the ALT Archives page
uparrowback to the Editorial Work page.

Valid HTML 4.1!