This volume contains all the papers presented
at the International Conference on Algorithmic Learning Theory 1999 (ALT'99),
held at Waseda University International Conference Center, Tokyo, Japan,
December 6 - 8, 1999.
The conference was sponsored
Japanese Society for Artificial Intelligence (JSAI).
In response to the call for papers, Fifty-one papers on all aspects of algorithmic learning theory and related areas were submitted, of which twenty-six papers were selected for presentation by the program committee based on their originality, quality, and relevance to the theory of machine learning. In addition to these regular papers, this volume contains three papers of invited lectures presented by Katharina Morik of University of Dortmund, Robert E. Schapire of AT & T Labs, Shannon Lab., and Kenji Yamanishi of NEC, C & C Media Research Lab.
ALT'99 is not just one of the ALT conference series, but this conference marks the Tenth Anniversary in the series that was launched out in Tokyo, October in 1990, for discussing research topics on all areas related to algorithmic learning theory. The ALT series was renamed last year from ``ALT workshop'' to ``ALT conference'', expressing its wider goal of providing an ideal forum to bring together researchers from both theoretical and practical learning communities, producing novel concepts and criteria that would benefit both. This movement was reflected in the papers presented this ALT'99 and there were several papers motivated application oriented problems such as noise, data precision, etc. Furthermore, ALT'99 was benefited from being held jointly with the 2nd International Conference on Discovery Science (DS'99), the conference for discussing, among others, more applied aspects of machine learning. Also we could celebrate the tenth anniversary of the ALT series with researchers from both theoretical and practical communities.
This year we started the E. Mark Gold Award for the most outstanding paper with a student author, selected by the program committee of the conference. This year's award is given to Yuri Kalnishkan for his paper ``General Linear Relations among Different Types of Predictive Complexity''.
We wish to thank all who have made this conference possible, first of all, to the authors for submitting papers and to three invited speakers for their excellent presentations and their contributions of papers to this volume.
We are indebted to all members of the program committee:
They and the subreferees (listed separately)* put a huge amount of work into reviewing the submissions and judging their importance and significance.
We also gratefully acknowledge all those who did important jobs behind the scenes to make this volume as well as the conference possible. Akira Maruoka for providing valuable suggestions, Shigeki Goto for the initial arrangement of a conference place, Naoki Abe for arranging an invited speaker, Shinichi Shimozono for producing ALT99 logo, Isao Saito for drawing ALT99 posters, and Springer-Verlag for their excellent support in preparing this volume.
Last but not least, we are very much grateful to all of the members of the Local Arrangement Committee: Taisuke Sato (chair), Satoru Miyano, Ayumi Shinohara, without their efforts this conference was absolutely impossible to be successful.
* The program committee likes to thank the following subreferees:
Hiroki Arimura, Sanghamitra Bandyopadhyay, Jonathan Baxter, Nicolo Cesa-Bianchi, Nello Cristianini, Stuart Flockton, Ryutaro Ichise, Kimihito Ito, Michael Kearns, Pascal Koiran, Eric Martin, Llew Mason, Ujjwal Maulik, Eric McCreath, Andrew Mitchell, Koichi Moriyama, Atsuyoshi Nakamura, Thomas R. Amoth, Mark Reid, Yasubumi Sakakibara, Hiroshi Sakamoto, Bernhard Schoelkopf, Rich Sutton, Noriyuki Tanida, Chris Watkins, Kenji Yamanishi, and Takashi Yokomori.