176 search results - page 4 / 36 » Generalization risk minimization in empirical game models |
AAAI
2012
11 years 9 months ago
2012
In large extensive form games with imperfect information, Counterfactual Regret Minimization (CFR) is a popular, iterative algorithm for computing approximate Nash equilibria. Whi...
NIPS
2001
13 years 8 months ago
2001
In this paper, it is shown how to extract a hypothesis with small risk from the ensemble of hypotheses generated by an arbitrary on-line learning algorithm run on an independent an...
JMLR
2010
13 years 1 months ago
2010
The problem of characterizing learnability is the most basic question of statistical learning theory. A fundamental and long-standing answer, at least for the case of supervised c...
ATAL
2010
Springer
13 years 8 months ago
2010
Springer
Games are used to evaluate and advance Multiagent and Artificial Intelligence techniques. Most of these games are deterministic with perfect information (e.g. Chess and Checkers)....
ICML
2010
IEEE
13 years 8 months ago
2010
IEEE
We address the problem of evaluating the risk of a given model accurately at minimal labeling costs. This problem occurs in situations in which risk estimates cannot be obtained f...