2006
NeurIPS
NeurIPS 2006
Optimal Single-Class Classification Strategies
Abstract
We consider single-class classification (SCC) as a two-person game between the learner and an adversary. In this game the target distribution is completely known to the learner and the learner's goal is to construct a classifier capable of guaranteeing a given tolerance for the false-positive error while minimizing the false negative error. We identify both "hard" and "soft" optimal classification strategies for different types of games and demonstrate that soft classification can provide a significant advantage. Our optimal strategies and bounds provide worst-case lower bounds for standard, finite-sample SCC and also motivate new approaches to solving SCC.
🚀
Conference Pioneer
- NeurIPS 2006
🌱
Topic Pioneer
- Adversarial Learning
📈
Trend Setter
- Adversarial Learning
🧭
Keyword Pioneer
- adversarial learning
🐣
Hot Topic Early Bird
- game theory
Authors
Topics
Artificial Intelligence > Core AI > Game AI
Machine Learning > Core Methods > Classification
Machine Learning > Learning Types > Adversarial Learning
Machine Learning > Optimization & Theory > Theory
Artificial Intelligence > Core AI > Adversarial Learning
Artificial Intelligence > Core AI > Game Theory