Preference-Based Batch and Sequential Teaching
Abstract
Algorithmic machine teaching studies the interaction between a teacher and a learner where the teacher selects labeled examples aiming at teaching a target hypothesis. In a quest to lower teaching complexity, several teaching models and complexity measures have been proposed for both the batch settings (e.g., worst-case, recursive, preference-based, and non-clashing models) and the sequential settings (e.g., local preference-based model). To better understand the connections between these models, we develop a novel framework that captures the teaching process via preference functions . In our framework, each function induces a teacher-learner pair with teaching complexity as . We show that the above-mentioned teaching models are equivalent to specific types/families of preference functions. We analyze several properties of the teaching complexity parameter associated with different families of the preference functions, e.g., comparison to the VC dimension of the hypothesis class and additivity/sub-additivity of over disjoint domains. Finally, we identify preference functions inducing a novel family of sequential models with teaching complexity linear in the VC dimension: this is in contrast to the best-known complexity result for the batch models, which is quadratic in the VC dimension.
Cite
@article{arxiv.2010.10012,
title = {Preference-Based Batch and Sequential Teaching},
author = {Farnam Mansouri and Yuxin Chen and Ara Vartanian and Xiaojin Zhu and Adish Singla},
journal= {arXiv preprint arXiv:2010.10012},
year = {2020}
}
Comments
arXiv admin note: substantial text overlap with arXiv:1910.10944