Search Improves Label for Active Learning
Authors: Alina Beygelzimer, Daniel J. Hsu, John Langford, Chicheng Zhang
NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We investigate active learning with access to two distinct oracles: LABEL (which is standard) and SEARCH (which is not). The SEARCH oracle models the situation where a human searches a database to seed or counterexample an existing solution. SEARCH is stronger than LABEL while being natural to implement in many situations. We show that an algorithm using both oracles can provide exponentially large problem-dependent improvements over LABEL alone. (...) The paper focuses on theoretical analyses of algorithms (LARCH, SEABEL, A-LARCH, AA-LARCH) and their query complexities, presenting theorems and proofs without reporting empirical results, dataset evaluations, or performance metrics. |
| Researcher Affiliation | Collaboration | Alina Beygelzimer Yahoo Research New York, NY beygel@yahoo-inc.com Daniel Hsu Columbia University New York, NY djhsu@cs.columbia.edu John Langford Microsoft Research New York, NY jcl@microsoft.com Chicheng Zhang UC San Diego La Jolla, CA chz038@cs.ucsd.edu |
| Pseudocode | Yes | Algorithm 1 LARCH (...) Algorithm 2 AA-LARCH |
| Open Source Code | No | The paper does not contain any statements or links indicating that source code for the described methodologies is available. |
| Open Datasets | No | The paper is theoretical and focuses on algorithm design and analysis. It does not use specific datasets for empirical evaluation, nor does it provide access information for any dataset. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical validation on datasets, thus no dataset splits for training, validation, or testing are discussed. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setups or report on empirical results that would necessitate specifying hardware used. |
| Software Dependencies | No | The paper is theoretical and focuses on algorithms and proofs. It does not mention any specific software dependencies or their version numbers required for implementation or reproduction. |
| Experiment Setup | No | The paper is theoretical and describes algorithms and their properties. It does not include an 'Experimental Setup' section or details on hyperparameters, training configurations, or system-level settings. |