Preference-based Teaching

Authors: Ziyuan Gao, Christoph Ries, Hans U. Simon, Sandra Zilles

JMLR 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce a new model of teaching named preference-based teaching and a corresponding complexity parameter the preference-based teaching dimension (PBTD) representing the worstcase number of examples needed to teach any concept in a given concept class. On top of presenting these concrete results, we provide the reader with a theoretical framework (of a combinatorial flavor) which helps to derive bounds on the PBTD.
Researcher Affiliation Academia Ziyuan Gao EMAIL Department of Computer Science, University of Regina Christoph Ries EMAIL Department of Mathematics, Ruhr-University Bochum Hans U. Simon EMAIL Department of Mathematics, Ruhr-University Bochum Sandra Zilles EMAIL Department of Computer Science, University of Regina
Pseudocode No The paper focuses on theoretical models, definitions, lemmas, and theorems. It does not contain any structured pseudocode or algorithm blocks.
Open Source Code No The paper cites an arXiv e-print (Gao et al., 2017) and a previous conference version (Gao et al., 2016). However, it does not contain any explicit statement or link indicating that source code for the described methodology is publicly available.
Open Datasets No The paper introduces a theoretical model and analyzes various concept classes (e.g., closed sets, linear sets, half-spaces) mathematically. It does not perform empirical evaluations using specific datasets, and thus, no dataset access information is provided.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets, so there is no mention of training/test/validation dataset splits.
Hardware Specification No The paper is theoretical and does not report on any computational experiments. Consequently, no hardware specifications are provided.
Software Dependencies No The paper focuses on theoretical aspects and does not involve computational experiments, thus no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not detail any empirical experiments. Therefore, there are no descriptions of experimental setup, hyperparameters, or training configurations.