Active clustering for labeling training data

Authors: Quentin Lutz, Elie de Panafieu, Maya Stein, Alex Scott

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In the first model, we characterize the algorithms that minimize the average number of queries required to cluster the items and analyze their complexity. In the second model, we analyze a specific algorithm family, propose as a conjecture that they reach the minimum average number of queries and compare their performance to a random approach. Our proofs, sketched in Section 3, rely on a broad variety of mathematical tools: probability theory, graph theory and analytic combinatorics.
Researcher Affiliation Collaboration Quentin Lutz Nokia Bell Labs quentin.lutz@nokia-bell-labs.com Élie de Panafieu Nokia Bell Labs elie.de_panafieu@nokia-bell-labs.com Alex Scott University of Oxford scott@maths.ox.ac.uk Maya Stein University of Chile mstein@dim.uchile.cl
Pseudocode No The paper describes algorithms verbally (e.g., 'The clique algorithm is an AC algorithm...', 'The universal algorithm finds the block...') but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to open-source code for the methodology it describes. It only references a third-party software system.
Open Datasets No The paper is theoretical and analyzes algorithms based on random models for set partitions, rather than using or providing access to empirical datasets for training.
Dataset Splits No The paper does not describe empirical experiments or specific training/validation/test dataset splits. It focuses on theoretical analysis of algorithms.
Hardware Specification No The paper focuses on theoretical research and does not mention any specific hardware used for running experiments or computations.
Software Dependencies Yes [22] The Sage Developers. Sage Math, the Sage Mathematics Software System (Version 9.0). https://www.sagemath.org. 2020.
Experiment Setup No The paper focuses on theoretical analysis of algorithms and does not describe any empirical experiment setup details, such as hyperparameters or training configurations.