Sciweavers

76
Voted
COLT
2000
Springer
15 years 5 months ago
Relative Expected Instantaneous Loss Bounds
Jürgen Forster, Manfred K. Warmuth
COLT
2000
Springer
15 years 5 months ago
On the Learnability and Design of Output Codes for Multiclass Problems
Output coding is a general framework for solving multiclass categorization problems. Previous research on output codes has focused on building multiclass machines given predefine...
Koby Crammer, Yoram Singer
72
Voted
COLT
2000
Springer
15 years 5 months ago
Logistic Regression, AdaBoost and Bregman Distances
Michael Collins, Robert E. Schapire, Yoram Singer
COLT
2000
Springer
15 years 5 months ago
Model Selection and Error Estimation
We study model selection strategies based on penalized empirical loss minimization. We point out a tight relationship between error estimation and data-based complexity penalizatio...
Peter L. Bartlett, Stéphane Boucheron, G&aa...
89
Voted
COLT
2000
Springer
15 years 5 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
106
Voted
COLT
2000
Springer
15 years 5 months ago
Adaptive and Self-Confident On-Line Learning Algorithms
Peter Auer, Claudio Gentile
COLT
2000
Springer
15 years 5 months ago
The Computational Complexity of Densest Region Detection
We investigate the computational complexity of the task of detecting dense regions of an unknown distribution from un-labeled samples of this distribution. We introduce a formal l...
Shai Ben-David, Nadav Eiron, Hans-Ulrich Simon
56
Voted
COLT
2000
Springer
15 years 5 months ago
On the Difficulty of Approximately Maximizing Agreements
Shai Ben-David, Nadav Eiron, Philip M. Long
73
Voted
ALT
2000
Springer
15 years 5 months ago
A Probabilistic Identification Result
Eric McCreath
92
Voted
ALT
2000
Springer
15 years 5 months ago
On the Hardness of Learning Acyclic Conjunctive Queries
A conjunctive query problem in relational database theory is a problem to determine whether or not a tuple belongs to the answer of a conjunctive query over a database. Here, a tup...
Kouichi Hirata