Teaching with Limited Information on the Learner’s Behaviour
Authors: Ferdinando Cicalese, Sergio Filho, Eduardo Laber, Marco Molinaro
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, to complement our theoretical results, we present in Section 5 experiments with 12 real datasets that show that our basic Teacher (the Aagno from Section 2) sends significantly fewer examples, to reach a given level of accuracy, than a Teacher that does not interact with the Learner. |
| Researcher Affiliation | Academia | 1Department of Computer Science, University of Verona, Italy 2Department of Computer Science, PUC-Rio, Brazil. |
| Pseudocode | Yes | Figure 1. Teacher s algorithm for teaching a realizable hypothesis |
| Open Source Code | No | No statement explicitly releasing source code for the described methodology or a link to a code repository was found. |
| Open Datasets | Yes | For our evaluation we used Random Forest and Light Gradient Boosting Machine (LGBM) as learners, and conducted experiments on 12 datasets: mnist and 11 others from the UCI repository (mushroom, avila, bank marketing, car, Credit Card, Firm Teacher, crowdsourced, Electrical grid, HTRU, nursery and Sensorless drive). |
| Dataset Splits | No | The paper mentions 'trained and tested in the full dataset' but does not specify explicit training/validation/test splits, percentages, or methodology for partitioning the data. |
| Hardware Specification | No | No specific hardware details (such as GPU/CPU models, memory, or processor types) used for running the experiments were provided in the paper. |
| Software Dependencies | No | The paper mentions 'Random Forest and Light Gradient Boosting Machine (LGBM)' but does not provide specific version numbers for these or any other software dependencies. |
| Experiment Setup | No | The paper does not provide specific experimental setup details such as hyperparameter values, training configurations, or system-level settings for the algorithms used. |