AdaBoost.MH
A decision-theoretic generalization of on-line learning and an application to boosting. In the first part of the paper we consider the problem of dynamically apportioning resources among a set of options in a worst-case on-line framework. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multiplicative weight-update Littlestone-Warmuth rule can be adapted to this model, yielding bounds that are slightly weaker in some cases, but applicable to a considerably more general class of learning problems. We show how the resulting learning algorithm can be applied to a variety of problems, including gambling, multiple-outcome prediction, repeated games, and prediction of points in $bfR^n$. In the second part of the paper we apply the multiplicative weight-update technique to derive a new boosting algorithm. This boosting algorithm does not require any prior knowledge about the performance of the weak learning algorithm. We also study generalizations of the new boosting algorithm to the problem of learning functions whose range, rather than being binary, is an arbitrary finite set or a bounded segment of the real line.
Keywords for this software
References in zbMATH (referenced in 504 articles , 1 standard article )
Showing results 1 to 20 of 504.
Sorted by year (- Battauz, Michela; Vidoni, Paolo: A likelihood-based boosting algorithm for factor analysis models with binary data (2022)
- Gao, Xuefeng; Xu, Tianrun: Order scoring, bandit learning and order cancellations (2022)
- Georgiev, Slavi G.; Vulkov, Lubin G.: Recovering the time-dependent volatility in jump-diffusion models from nonlocal price observations (2022)
- Huber, Florian; Rossini, Luca: Inference in Bayesian additive vector autoregressive tree models (2022)
- Rudin, Cynthia; Chen, Chaofan; Chen, Zhi; Huang, Haiyang; Semenova, Lesia; Zhong, Chudi: Interpretable machine learning: fundamental principles and 10 grand challenges (2022)
- Tchuente, Dieudonné; Nyawa, Serge: Real estate price estimation in French cities using geocoding and machine learning (2022)
- Werner, Tino: A review on instance ranking problems in statistical learning (2022)
- Ahmmed, B.; Mudunuru, M. K.; Karra, S.; James, S. C.; Vesselinov, V. V.: A comparative study of machine learning models for predicting the state of reactive mixing (2021)
- Altschuler, Jason M.; Talwar, Kunal: Online learning over a finite action set with limited switching (2021)
- Arlazarov, Vladimir Viktorovich; Voĭsyat, Yuliya Sergeevich; Matalov, Daniil Pavlovich; Nikolaev, Dmitriĭ Petrovich; Usilin, Sergeĭ Aleksandrovich: Evolution of the Viola-Jones object detection method: a survey (2021)
- Bartlett, Peter L. (ed.); Butucea, Cristina (ed.); Schmidt-Hieber, Johannes (ed.): Mathematical foundations of machine learning. Abstracts from the workshop held March 21--27, 2021 (hybrid meeting) (2021)
- Bulavas, Viktoras; Marcinkevičius, Virginijus; Rumiński, Jacek: Study of multi-class classification algorithms’ performance on highly imbalanced network intrusion datasets (2021)
- Calder, Jeff; Drenska, Nadejda: Asymptotically optimal strategies for online prediction with history-dependent experts (2021)
- Carrizosa, Emilio; Molero-Río, Cristina; Romero Morales, Dolores: Mathematical optimization in classification and regression trees (2021)
- Cheng, Yichen; Wang, Xinlei; Xia, Yusen: Supervised (t)-distributed stochastic neighbor embedding for data visualization and classification (2021)
- Conde, David; Fernández, Miguel A.; Rueda, Cristina; Salvador, Bonifacio: Isotonic boosting classification rules (2021)
- Feng, Chen; Griffin, Paul; Kethireddy, Shravan; Mei, Yajun: A boosting inspired personalized threshold method for sepsis screening (2021)
- Field, Duncan; Ammouche, Yanis; Peña, José-Maria; Jérusalem, Antoine: Machine learning based multiscale calibration of mesoscopic constitutive models for composite materials: application to brain white matter (2021)
- Ghosal, Indrayudh; Hooker, Giles: Boosting random forests to reduce bias; one-step boosted forest and its variance estimate (2021)
- Gweon, Hyukjun; Li, Shu: Batch mode active learning framework and its application on valuing large variable annuity portfolios (2021)