Interactive Algorithms: Pool, Stream and Precognitive Stream
Authors: Sivan Sabato, Tom Hess
JMLR 2017 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide algorithms and matching lower bounds for general pool algorithms, and for utility-based pool algorithms. We further derive nearly matching upper and lower bounds on the gap between the two settings for the special case of active learning for binary classification. |
| Researcher Affiliation | Academia | Sivan Sabato EMAIL Tom Hess EMAIL Department of Computer Science Ben-Gurion University of the Negev Beer Sheva 8410501, Israel. |
| Pseudocode | Yes | Algorithm 1 Algorithm Await Algorithm 2 Algorithm Anowait Algorithm 3 Algorithm Agen Algorithm 4 AU p Algorithm 5 Sec Pr Var Algorithm 6 AU s |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. It only provides licensing information for the paper itself. |
| Open Datasets | No | The paper discusses abstract elements and responses drawn from theoretical distributions, such as 'Let D be a distribution over X Y'. It does not refer to any specific publicly available or open datasets for empirical evaluation. |
| Dataset Splits | No | The paper focuses on theoretical analysis and does not conduct experiments using specific datasets, therefore, no dataset split information is provided. |
| Hardware Specification | No | The paper is theoretical and does not describe any experimental setups requiring specific hardware, thus no hardware specifications are provided. |
| Software Dependencies | No | The paper is theoretical and presents algorithms in pseudocode. It does not describe any implementation details that would require listing specific software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical, presenting algorithms and mathematical proofs. It does not include an experimental section with specific setup details, hyperparameters, or training configurations. |