MAP- and MLE-Based Teaching
Authors: Hans Ulrich Simon, Jan Arne Telle
JMLR 2024 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | Our main results are as follows. First, we show that this teaching model has some desirable monotonicity properties. Second we clarify how the four sampling modes are related to each other. As for the (important!) special case, where concepts are subsets of a domain and observations are 0,1-labeled examples, we obtain some additional results. First of all, we characterize the MAPand MLE-teaching dimension associated with an optimally parameterized MAP-learner graph-theoretically. From this central result, some other ones are easy to derive. It is shown, for instance, that the MLE-teaching dimension is either equal to the MAP-teaching dimension or exceeds the latter by 1. It is shown furthermore that these dimensions can be bounded from above by the so-called antichain number, the VC-dimension and related combinatorial parameters. Moreover they can be computed in polynomial time. |
| Researcher Affiliation | Academia | Hans Ulrich Simon EMAIL Max-Planck Institute for Informatics, Germany and Ruhr-University Bochum, Department of Mathematics, Germany Jan Arne Telle EMAIL Department of Informatics, University of Bergen, Norway |
| Pseudocode | No | The paper describes methods through mathematical formulations and theorems, not structured pseudocode or algorithm blocks. While Lemma 37 describes an 'oracle algorithm', it refers to a theoretical algorithmic process rather than providing pseudocode for implementation. |
| Open Source Code | No | The paper does not contain any explicit statements about releasing source code, nor does it provide links to a code repository. |
| Open Datasets | No | The paper introduces abstract concept classes (C) and observation sets (Z) and provides examples (Example 1, 2, 3) for theoretical illustration, but does not use or reference any specific publicly available datasets for experiments. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical evaluation on datasets, thus no dataset split information is provided. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setup or hardware used for computations. |
| Software Dependencies | No | The paper is theoretical and does not detail any specific software dependencies with version numbers required to replicate experimental results. |
| Experiment Setup | No | The paper is theoretical and does not include details on experimental setup, hyperparameters, or training configurations. |