Gradient-based Algorithms for Machine Teaching

The problem of machine teaching is considered. A new formulation is proposed under the assumption of an optimal student, where optimality is defined in the usual machine learning sense of empirical risk minimization. This is a sensible assumption for machine learning students and for human students...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) s. 1387 - 1396
Hlavní autoři: Wang, Pei, Nagrecha, Kabir, Vasconcelos, Nuno
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.06.2021
Témata:
Classification algorithms
Education
Machine learning algorithms
Pattern recognition
Risk management
Sociology
Training
ISSN:1063-6919
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The problem of machine teaching is considered. A new formulation is proposed under the assumption of an optimal student, where optimality is defined in the usual machine learning sense of empirical risk minimization. This is a sensible assumption for machine learning students and for human students in crowdsourcing platforms, who tend to perform at least as well as machine learning systems. It is shown that, if allowed unbounded effort, the optimal student always learns the optimal predictor for a classification task. Hence, the role of the optimal teacher is to select the teaching set that minimizes student effort. This is formulated as a problem of functional optimization where, at each teaching iteration, the teacher seeks to align the steepest descent directions of the risk of (1) the teaching set and (2) entire example population. The optimal teacher, denoted MaxGrad, is then shown to maximize the gradient of the risk on the set of new examples selected per iteration. MaxGrad teaching algorithms are finally provided for both binary and multiclass tasks, and shown to have some similarities with boosting algorithms. Experimental evaluations demonstrate the effectiveness of MaxGrad, which outperforms previous algorithms on the classification task, for both machine learning and human students from MTurk, by a substantial margin.
ISSN:1063-6919
DOI:10.1109/CVPR46437.2021.00144