Incremental Clustering: The Case for Extra Clusters
Authors: Margareta Ackerman, Sanjoy Dasgupta
NeurIPS 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this paper, we initiate the formal analysis of incremental clustering methods focusing on the types of cluster structure that they are able to detect. We find that the incremental setting is strictly weaker than the batch model, proving that a fundamental class of cluster structures that can readily be detected in the batch setting is impossible to identify using any incremental method. Furthermore, we show how the limitations of incremental clustering can be overcome by allowing additional clusters. |
| Researcher Affiliation | Academia | Margareta Ackerman Florida State University 600 W College Ave, Tallahassee, FL 32306 mackerman@fsu.edu Sanjoy Dasgupta UC San Diego 9500 Gilman Dr, La Jolla, CA 92093 dasgupta@eng.ucsd.edu |
| Pseudocode | Yes | Algorithm 2.2. Sequential k-means. ... Algorithm 2.3. Sequential agglomerative clustering. ... Algorithm 2.4. Sequential nearest-neighbour clustering. ... Algorithm 5.2. Incremental clustering with extra centers. ... Algorithm 5.9. Algorithm subsample. |
| Open Source Code | No | The paper does not provide any links or explicit statements about making its source code publicly available. |
| Open Datasets | No | The paper is theoretical and does not conduct experiments on specific datasets requiring public access information for training data. |
| Dataset Splits | No | The paper is theoretical and does not conduct experiments with dataset splits for validation. |
| Hardware Specification | No | The paper is theoretical and does not describe any specific hardware used for experiments. |
| Software Dependencies | No | The paper is theoretical and focuses on algorithms and proofs; it does not specify any software dependencies with version numbers for implementation or replication. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with hyperparameters or system-level training settings. |