Optimal Weak to Strong Learning

Authors: Kasper Green Larsen, Martin Ritzert

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

Reproducibility Variable Result LLM Response
Research Type Theoretical Our work is purely theoretic (set within learning theory) and is thus not expected to impact society outside of the scientific community
Researcher Affiliation Academia Kasper Green Larsen Department of Computer Science Aarhus University Aarhus, Denmark larsen@cs.au.dk Martin Ritzert Department of Computer Science Aarhus University Aarhus, Denmark ritzert@cs.au.dk
Pseudocode Yes Algorithm 1: Sub-Sample(A, B) Algorithm 2: Optimal weak-to-strong learner
Open Source Code No (a) Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No The paper is theoretical and does not describe using any dataset for training. The Ethics Review Checklist states 'N/A' for questions related to experiments and data.
Dataset Splits No The paper is theoretical and does not describe any experimental validation using dataset splits. The Ethics Review Checklist states 'N/A' for questions related to experiments and data.
Hardware Specification No The paper is purely theoretical and does not describe any experimental hardware. The Ethics Review Checklist states 'N/A' for 'total amount of compute and the type of resources used'.
Software Dependencies No The paper is purely theoretical and does not describe any software dependencies with specific version numbers for experimental reproducibility. The Ethics Review Checklist states 'N/A' for 'include the code'.
Experiment Setup No The paper is purely theoretical and does not describe an experimental setup with hyperparameters or training details. The Ethics Review Checklist states 'N/A' for 'specify all the training details'.