Active Bipartite Ranking
Authors: James Cheshire, Vincent Laurent, Stephan Clémençon
NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Beyond the theoretical analysis carried out, numerical results are presented, providing strong empirical evidence of the performance of the algorithm proposed, which compares favorably with more naive approaches. 4 Experiments In this section we discuss practical cases based on synthetic data. For all experiments δ is fixed at 0.01 and the constants used are smaller than their theoretical counterparts, which are typically overestimated, furthermore bp is calculated with all previous samples. As represented in Figure 3, each cell i is assigned a level value µi so that η follows the Assumption 2.1. Without loss of generality, we assume that η can be described as an increasing family (µi)i [K]. Our study scenarios are then as follows: |
| Researcher Affiliation | Academia | James Cheshire Stephan Clemencon Telecom Paris Tech first.last@telecom-paris.fr Vincent Laurent ENS Paris Saclay first.last@ens-paris-saclay.fr |
| Pseudocode | Yes | Algorithm 1 active-rank |
| Open Source Code | No | The paper does not provide any specific links or statements about the availability of open-source code for their proposed method. |
| Open Datasets | No | The paper uses 'synthetic data' with manually defined scenarios and parameters (e.g., Scenario 1: (µi)i [K] = (0, 0.28, 0.3, 0.38) and K = 16), which are not publicly available datasets or provided with concrete access information. |
| Dataset Splits | No | The paper mentions 'synthetic data' and '100 realizations' for Monte Carlo estimation, but does not specify explicit training, validation, or test dataset splits (e.g., percentages or sample counts) needed for reproduction. |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers (e.g., programming languages, libraries, frameworks). |
| Experiment Setup | No | The paper describes the synthetic data scenarios and the competing algorithms in Section 4, but does not provide specific experimental setup details such as hyperparameters (e.g., learning rate, batch size, number of epochs) for the active-rank algorithm, beyond stating that 'δ is fixed at 0.01 and the constants used are smaller than their theoretical counterparts'. |