Special Issue on

Algorithmic Learning Theory

for ALT 2010 in

Theoretical Computer Science

ALT 10 Logo

appeared as:

Theoretical Computer Science, Volume 473, February 18, 2013.

The Special Issue on Algorithmic Learning Theory has been edited by Marcus Hutter, Frank Stephan, Vladimir Vovk, and Thomas Zeugmann

Table of Contents

Marcus Hutter, Frank Stephan, Vladimir Vovk, and Thomas Zeugmann.
Guest Editors' foreword,

pp. 1–3

Guy Lever, François Laviolette and John Shawe-Taylor.
Tighter PAC-Bayes bounds through distribution-dependent priors,

pp. 4–28

Vladimir Pestov.
PAC learnability under non-atomic measures: A problem by Vidyasagar,
pp. 29–45

Borja Balle, Jorge Castro, and Ricard Gavaldà.
Learning probabilistic automata: A study in state distinguishability,
pp. 46–60

Wouter M. Koolen and Steven de Rooij
Switching investments ,
pp. 61–76

András Antos, Gábor Bartók, Dávid Pál, and Csaba Szepesvári.
Toward a classification of finite partial-monitoring games ,
pp. 77–99

John Case and Timo Kötzing
Memory-limited non-U-shaped learning with solved open problems,
pp. 100–123

Sanjay Jain, Samuel E. Moelius III, and Sandra Zilles.
Learning without coding,
pp. 124–148

Laurent Orseau.
Asymptotic non-learnability of universal agents with computable horizon functions,
pp. 149–156

Fedor Zhdanov and Yuri Kalnishkan.
An identity for kernel ridge regression,
pp. 157–178

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

Valid HTML 4.1!