Semi-Supervised Clustering Of Stable Instances.
Date of Submission
December 2018
Date of Award
Winter 12-12-2019
Institute Name (Publisher)
Indian Statistical Institute
Document Type
Master's Dissertation
Degree Name
Master of Technology
Subject Name
Computer Science
Department
Electronics and Communication Sciences Unit (ECSU-Kolkata)
Supervisor
Das, Swagatam (ECSU-Kolkata; ISI)
Abstract (Summary of the Work)
Clustering is one of the fundamental problems in data mining. Various objective functions, like k-means, k-median, k-mediod have been applied to solve clustering problems. While all these objectives are NP-Hard in the worst case, practitioners have found remarkable success in applying heuristics like Lloyd’s algorithm for this problem. The following question then becomes important: what properties of real-world instances will enable us to design efficient algorithms and prove guarantees for finding the optimal clustering? We consider the case of multiplicative perturbation stability. Stable instances have an optimal solution that does not change when the distances are perturbed. This captures the notion that optimal solution is tolerant to measurement errors and uncertainty in the points. Semi-supervision allows us to have an oracle O which answers pairwise queries. We design efficient algorithms which solve problems of multiplicative perturbation stability using a noisy oracle model.
Control Number
ISI-DISS-2018-381
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.
DOI
http://dspace.isical.ac.in:8080/jspui/handle/10263/6947
Recommended Citation
Sanyal, Deepayan, "Semi-Supervised Clustering Of Stable Instances." (2019). Master’s Dissertations. 212.
https://digitalcommons.isical.ac.in/masters-dissertations/212
Comments
ProQuest Collection ID: http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqm&rft_dat=xri:pqdiss:28843235