Modern aspects of unsupervised learning

Liang, Yingyu

Title:

Modern aspects of unsupervised learning

dc.contributor.advisor	Balcan, Maria-Florina
dc.contributor.author	Liang, Yingyu
dc.contributor.committeeMember	Blum, Avrim
dc.contributor.committeeMember	Fortnow, Lance
dc.contributor.committeeMember	Isbell, Charles L.
dc.contributor.committeeMember	Randall, Dana
dc.contributor.committeeMember	Song, Le
dc.contributor.department	Computer Science
dc.date.accessioned	2014-08-27T13:38:49Z
dc.date.available	2014-08-27T13:38:49Z
dc.date.created	2014-08
dc.date.issued	2014-06-23
dc.date.submitted	August 2014
dc.date.updated	2014-08-27T13:38:49Z
dc.description.abstract	Unsupervised learning has become more and more important due to the recent explosion of data. Clustering, a key topic in unsupervised learning, is a well-studied task arising in many applications ranging from computer vision to computational biology to the social sciences. This thesis is a collection of work exploring two modern aspects of clustering: stability and scalability. In the first part, we study clustering under a stability property called perturbation resilience. As an alternative approach to worst case analysis, this novel theoretical framework aims at understanding the complexity of clustering instances that satisfy natural stability assumptions. In particular, we show how to correctly cluster instances whose optimal solutions are resilient to small multiplicative perturbations on the distances between data points, significantly improving existing guarantees. We further propose a generalized property that allows small changes in the optimal solutions after perturbations, and provide the first known positive results in this more challenging setting. In the second part, we study the problem of clustering large scale data distributed across nodes which communicate over the edges of a connected graph. We provide algorithms with small communication cost and provable guarantees on the clustering quality. We also propose algorithms for distributed principal component analysis, which can be used to reduce the communication cost of clustering high dimensional data while merely comprising the clustering quality. In the third part, we study community detection, the modern extension of clustering to network data. We propose a theoretical model of communities that are stable in the presence of noisy nodes in the network, and design an algorithm that provably detects all such communities. We also provide a local algorithm for large scale networks, whose running time depends on the sizes of the output communities but not that of the entire network.
dc.description.degree	Ph.D.
dc.format.mimetype	application/pdf
dc.identifier.uri	http://hdl.handle.net/1853/52282
dc.language.iso	en_US
dc.publisher	Georgia Institute of Technology
dc.subject	Unsupervised learning
dc.subject	Clustering
dc.subject	Perturbation resilience
dc.subject	Distributed clustering
dc.subject	Community detection
dc.title	Modern aspects of unsupervised learning
dc.type	Text
dc.type.genre	Dissertation
dspace.entity.type	Publication
local.contributor.corporatename	College of Computing
relation.isOrgUnitOfPublication	c8892b3c-8db6-4b7b-a33a-1b67f7db2021
thesis.degree.level	Doctoral