Non-Cheating Teaching Revisited: A New Probabilistic Machine Teaching Model

Authors: Cèsar Ferri, José Hernández-Orallo, Jan Arne Telle

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Overall, this new setting is more general than the traditional machine teaching models, yet at the same time more intuitively capturing a less abrupt notion of non-cheating teaching. We show a simple procedure that builds the witness joint distribution from the ground joint distribution. We prove a chain of relations, also with a theoretical lower bound, on the teaching dimension of the old and new models.
Researcher Affiliation Academia C esar Ferri 1 , Jos e Hern andez-Orallo 1 , Jan Arne Telle 2 1 VRAIN, Universitat Polit ecnica de Val encia, Spain. 2 Department of Informatics, University of Bergen, Norway.
Pseudocode No The paper contains no pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statements about releasing source code or links to a code repository.
Open Datasets No This is a theoretical paper and does not involve training on datasets.
Dataset Splits No This is a theoretical paper and does not involve dataset splits for validation.
Hardware Specification No The paper is theoretical and does not describe any hardware specifications used for experiments.
Software Dependencies No The paper is theoretical and does not mention any software dependencies with specific version numbers.
Experiment Setup No The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings.