> ML_LITERATURE // FREUND-SCHAPIRE-1997-DECISION-THEORETIC-GENERALIZATION-ON-LINE-LEARNING-ADABOOST_v1.0
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting (AdaBoost)
Yoav Freund, Robert E. Schapire · Journal of Computer and System Sciences (1997)
foundational1997industry-standardthirdPartyReproduced
Principal Contribution
Introduced AdaBoost (Adaptive Boosting), provably converting an ensemble of weak base learners into an arbitrarily strong classifier.
Operational Relevance
Serves as canonical technical reference for implementing task-binary-classification in production systems.
Assumptions
- Underlying data distribution satisfies empirical consistency and regularity assumptions across training domains
Limitations
- Scaling characteristics and accuracy depend on hardware architecture, parameter scale, and dataset quality
Connected Algorithms, Architectures & Tools
Related Algorithms:
Related Architectures:
Implementing Libraries: