Achieving Minimax Rates in Pool-Based Batch Active Learning
Authors: Claudio Gentile, Zhilei Wang, Tong Zhang
ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We theoretically investigate batch active learning in the practically relevant scenario where the unlabeled pool of data is available beforehand (pool-based active learning). We analyze a novel stage-wise greedy algorithm and show that, as a function of the label complexity, the excess risk of this algorithm matches the known minimax rates in standard statistical learning settings. Our results also exhibit a mild dependence on the batch size. These are the first theoretical results that employ careful trade offs between informativeness and diversity to rigorously quantify the statistical performance of batch active learning in the pool-based scenario. |
| Researcher Affiliation | Collaboration | 1Google Research, New York 2Citadel Securities, New York 3The Hong Kong University of Science and Technology, Hong Kong. |
| Pseudocode | Yes | Algorithm 1: Pool-based batch active learning algorithm for linear models. |
| Open Source Code | No | The paper does not mention the availability of open-source code for the described methodology. |
| Open Datasets | No | The paper discusses a 'pool P of T unlabeled instances x1, . . . , x T X' for theoretical analysis but does not mention a specific, publicly available dataset used for empirical training. |
| Dataset Splits | No | The paper is theoretical and does not discuss training/validation/test dataset splits. |
| Hardware Specification | No | The paper does not mention any specific hardware specifications used for running experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The paper focuses on theoretical algorithms and analysis, and does not include details about an empirical experimental setup such as hyperparameters or system-level training settings. |