Active Learning of General Halfspaces: Label Queries vs Membership Queries

Authors: Ilias Diakonikolas, Daniel Kane, Mingchen Ma

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper focuses on theoretical analysis, presenting information-theoretic lower bounds, algorithms, and proofs (e.g., "We study the problem of learning general...", "Theorem 1.1 (Main Lower Bound)", "Theorem 1.2 (Main Algorithmic Result)", "Proof of Lemma 2.1", "Appendix G for the full proof of Theorem 1.2"). The NeurIPS checklist explicitly states: "This paper is theoretical and does not contain experiments."
Researcher Affiliation Academia Ilias Diakonikolas University of Wisconsin-Madison ilias@cs.wisc.edu Daniel M. Kane University of California, San Diego dakane@cs.ucsd.edu Mingchen Ma University of Wisconsin-Madison mingchen@cs.wisc.edu
Pseudocode Yes Algorithm 1 QUERY LEARNING HALFSPACE, Algorithm 2 INITIALIZATION 1, Algorithm 3 REFINE, Algorithm 4 ANGLE TEST, Algorithm 5 INITIALIZATION 2
Open Source Code No This paper is theoretical and does not mention releasing code, providing a link, or stating code is in supplementary material.
Open Datasets No This paper is theoretical and does not involve experiments with datasets. Therefore, it does not provide concrete access information for a publicly available or open dataset.
Dataset Splits No This paper is theoretical and does not involve experiments or dataset evaluation. Therefore, it does not provide specific dataset split information for training, validation, or testing.
Hardware Specification No This paper is theoretical and does not describe experimental procedures that would require specific hardware specifications.
Software Dependencies No This paper is theoretical and does not describe experimental procedures that would require specific software dependencies with version numbers.
Experiment Setup No This paper is theoretical and does not describe experimental setups, hyperparameters, or training configurations.