Fetching the paper…

Reading the bibliography…

2012

Clustering is difficult only when it does not matter

Daniely, Amit, Linial, Nati, Saks, Michael

Original
PDF
Post on X

Understand

Numerous papers ask how difficult it is to cluster data.

We suggest that the more relevant and interesting question is how difficult it is to cluster data sets {\em that can be clustered well}.
More generally, despite the ubiquity and the great importance of clustering, we still do not have a satisfactory mathematical theory of clustering.
In order to properly understand clustering, it is clearly necessary to develop a solid theoretical basis for the area.

Clustering is difficult only when it does not matter · Around

Built on

Computers and Intractability: A Guide to the Theory of NP-Completeness
M. Garey and D. Johnson · 1979
Earlier work this paper cites.
An impossibility theorem for clustering
Original
J. Kleinberg · 2002
Earlier work this paper cites.
Which data sets are ”clusterable”? – a theoretical study of clusterability
M. Ackerman and S. Ben-David · 2008
Earlier work this paper cites.

Similar

A discriminative framework for clustering via similarity functions
M.F. Balcan, A. Blum, and S. Vempala · 2008
Cited alongside, same era.
Thoughts on clustering
Avrim Blum · 2009
Cited alongside, same era.
Are stable instances easy?
Y. Bilu and N. Linial · 2010
Cited alongside, same era.

Then

Center-based clustering under perturbation stability
P. Awasthi, A. Blum, and O. Sheffet · 2011
Later among the works it cites.
On the furthest hyperplane problem and maximal margin clustering
Z. S. Karnin, E. Liberty, S. Lovett, R. Schwartz, and O. Weinshtein · 2011
Later among the works it cites.
Finding overlapping communities in social networks: Toward a rigorous approach
Original
Sanjeev Arora, Rong Ge, Sushant Sachdeva, and Grant Schoenebeck · 2012
Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…