all-bibliography.bib
@inproceedings{Andersen-2011-overlapping-csc,
author = {Andersen, Reid and Gleich, David F. and Mirrokni, Vahab S},
title = {Overlapping clusters for distributed computation},
booktitle = {Poster proceedings of the SIAM Workshop on Combinatorial and Scientific
Computing (CSC)},
year = {2011},
note = {Poster.},
file = {:Andersen 2011 - overlapping poster.pdf:PDF},
keywords = {self},
owner = {dgleich},
timestamp = {2011.10.26}
}
@inproceedings{bayati2009-network-alignment,
author = {Mohsen Bayati and Margot Gerritsen and David F. Gleich and Amin Saberi
and Ying Wang},
title = {Algorithms for Large, Sparse Network Alignment Problems},
booktitle = {Proceedings of the 9th IEEE International Conference on Data Mining},
year = {2009},
pages = {705-710},
month = {December},
abstract = {We propose a new distributed algorithm for sparse variants of the
network alignment problem that occurs in a variety of data mining
areas including systems biology, database matching, and computer
vision. Our algorithm uses a belief propagation heuristic and provides
near optimal solutions for an NP-hard combinatorial optimization
problem. We show that our algorithm is faster and outperforms or
nearly ties existing algorithms on synthetic problems, a problem
in bioinformatics, and a problem in ontology matching. We also provide
a unified framework for studying and comparing all network alignment
solvers.},
doi = {10.1109/ICDM.2009.135},
eprint = {0907.3338},
file = {:bayati 2009 - network alignment.pdf:PDF},
owner = {David F. Gleich},
timestamp = {2009.07.20}
}
@inproceedings{constantine2007-pagerank-pce,
author = {Paul G. Constantine and David F. Gleich},
title = {Using Polynomial Chaos to Compute the Influence of Multiple Random
Surfers in the {PageRank} Model},
booktitle = {Proceedings of the 5th Workshop on Algorithms and Models for the
Web Graph ({WAW2007})},
year = {2007},
editor = {Anthony Bonato and Fan Chung Graham},
volume = {4863},
series = {Lecture Notes in Computer Science},
pages = {82--95},
publisher = {Springer},
abstract = {The PageRank equation computes the importance of pages in a web graph
relative to a single random surfer with a constant teleportation
coefficient. To be globally relevant, the teleportation coefficient
should account for the influence of all users. Therefore, we correct
the PageRank formulation by modeling the teleportation coefficient
as a random variable distributed according to user behavior. With
this correction, the PageRank values themselves become random. We
present two methods to quantify the uncertainty in the random PageRank:
a Monte Carlo sampling algorithm and an algorithm based the truncated
polynomial chaos expansion of the random quantities. With each of
these methods, we compute the expectation and standard deviation
of the PageRanks. Our statistical analysis shows that the standard
deviation of the PageRanks are uncorrelated with the PageRank vector.},
doi = {10.1007/978-3-540-77004-6_7},
file = {:constantine2007 - pagerank pce.pdf:PDF},
key = {CG2007},
keywords = {self, pagerank, polynomial chaos,},
owner = {David Gleich},
timestamp = {2007.10.10}
}
@conference{Constantine-2011-MRTSQR,
author = {Constantine, Paul G. and Gleich, David F.},
title = {Tall and skinny {QR} factorizations in {MapReduce} architectures},
booktitle = {Proceedings of the second international workshop on MapReduce and
its applications},
year = {2011},
series = {MapReduce '11},
pages = {43--50},
address = {New York, NY, USA},
publisher = {ACM},
acmid = {1996103},
doi = {10.1145/1996092.1996103},
file = {:Constantine 2011 - TSQR.pdf:PDF},
isbn = {978-1-4503-0700-0},
keywords = {Hadoop, QR factorization, linear regression, matrix factorization,
tsqr},
location = {San Jose, California, USA},
numpages = {8},
owner = {David F. Gleich},
timestamp = {2011.06.18}
}
@inproceedings{decoste2005-recommender,
author = {Dennis Decoste and David F. Gleich and Tejaswi Kasturi and Sathiya
Keerthi and Omid Madani and Seung-Taek Park and David M. Pennock
and Corey Porter and Sumit Sanghai and Farial Shahnaz and Leonid
Zhukov},
title = {Recommender Systems Research at {Yahoo! Research Labs}},
booktitle = {Beyond Personalization},
year = {2005},
address = {San Diego, CA},
month = {January},
note = {Position Statement},
abstract = {We describe some of the ongoing projects at Yahoo! Research
Labs that involve recommender systems. We discuss
recommender systems related problems and solutions relevant
to Yahoo!’s business.},
file = {:decoste2005 - yahoo recommender systems.pdf:PDF},
key = {DGK+05},
keywords = {self, recommender systems},
owner = {David Gleich},
timestamp = {2006.10.13}
}
@inproceedings{esfandiar2010-fast-katz,
author = {Pooya Esfandiar and Francesco Bonchi and David F. Gleich and Chen
Greif and Laks V. S. Lakshmanan and Byung-Won On},
title = {Fast {Katz} and Commuters: Efficient Approximation of Social Relatedness
over Large Networks},
booktitle = {Algorithms and Models for the Web Graph},
year = {2010},
abstract = {Motivated by social network data mining problems such as link prediction
and collaborative filtering, significant research effort has been
devoted to computing topological measures including the Katz score
and the commute time. Existing approaches typically approximate all
pairwise relationships simultaneously. In this paper, we are interested
in computing: the score for a single pair of nodes, and the top-k
nodes with the best scores from a given source node. For the pairwise
problem, we apply an iterative algorithm that computes upper and
lower bounds for the measures we seek. This algorithm exploits a
relationship between the Lanczos process and a quadrature rule. For
the top-k problem, we propose an algorithm that only accesses a small
portion of the graph and is related to techniques used in personalized
PageRank computing. To test the scalability and accuracy of our algorithms
we experiment with three real-world networks and find that these
algorithms run in milliseconds to seconds without any preprocessing.},
doi = {10.1007/978-3-642-18009-5_13},
file = {:esfandiar 2010 - fast katz.pdf:PDF},
keywords = {self},
owner = {David Gleich},
timestamp = {2010.04.08}
}
@inproceedings{constantine2010-teleportation,
author = {David F. Gleich and Paul G. Constantine and Abraham Flaxman and Asela
Gunawardana},
title = {Tracking the random surfer: empirically measured teleportation parameters
in {PageRank}},
booktitle = {WWW '10: Proceedings of the 19th international conference on World
wide web},
year = {2010},
pages = {381--390},
month = {April},
abstract = {PageRank computes the importance of each node in a directed graph
under a random surfer model governed by a teleportation parameter.
Commonly denoted alpha, this parameter models the probability of
following an edge inside the graph or, when the graph comes from
a network of web pages and links, clicking a link on a web page.
We empirically measure the teleportation parameter based on browser
toolbar logs and a click trail analysis. For a particular user or
machine, such analysis produces a value of alpha. We find that these
values nicely fit a Beta distribution with mean edge-following probability
between 0.3 and 0.7, depending on the site. Using these distributions,
we compute PageRank scores where PageRank is computed with respect
to a distribution as the teleportation parameter, rather than a constant
teleportation parameter. These new metrics are evaluated on the graph
of pages in Wikipedia.},
doi = {10.1145/1772690.1772730},
file = {:gleich 2010 - tracking the random surfer.pdf:PDF},
isbn = {978-1-60558-799-8},
keywords = {self},
location = {Raleigh, North Carolina, USA},
owner = {David F. Gleich},
timestamp = {2009.12.03}
}
@inproceedings{Gleich-2011-skew-nuclear,
author = {Gleich, David F. and Lim, Lek-Heng},
title = {Rank aggregation via nuclear norm minimization},
booktitle = {Proceedings of the 17th ACM SIGKDD international conference on Knowledge
discovery and data mining},
year = {2011},
series = {KDD '11},
pages = {60--68},
address = {New York, NY, USA},
publisher = {ACM},
abstract = {The process of rank aggregation is intimately intertwined with the
structure of skew-symmetric matrices. We apply recent advances in
the theory and algorithms of matrix completion to skew-symmetric
matrices. This combination of ideas produces a new method for ranking
a set of items. The essence of our idea is that a rank aggregation
describes a partially filled skew-symmetric matrix. We extend an
algorithm for matrix completion to handle skew-symmetric data and
use that to extract ranks for each item. Our algorithm applies to
both pairwise comparison and rating data. Because it is based on
matrix completion, it is robust to both noise and incomplete data.
We show a formal recovery result for the noiseless case and present
a detailed study of the algorithm on synthetic data and Netflix ratings.},
acmid = {2020425},
doi = {10.1145/2020408.2020425},
file = {:Gleich 2011 - rank aggregation.pdf:PDF},
isbn = {978-1-4503-0813-7},
keywords = {self, nuclear norm, rank aggregation, skew symmetric},
location = {San Diego, California, USA},
numpages = {9},
owner = {David F. Gleich},
timestamp = {2010.01.30}
}
@inproceedings{gleich2005-ppagerank,
author = {David F. Gleich and Leonid Zhukov},
title = {Scalable Computing with Power-Law Graphs: Experience with Parallel
{PageRank}},
booktitle = {SuperComputing 2005},
year = {2005},
month = {November},
note = {Poster.},
file = {:gleich2005 - parallel pagerank.pdf:PDF},
key = {GZ2005},
keywords = {self, pagerank},
owner = {David Gleich},
timestamp = {2006.10.13},
url = {http://www.cs.purdue.edu/homes/dgleich/publications/gleich2005 - parallel pagerank.pdf}
}
@inproceedings{gleich2004-svd,
author = {David F. Gleich and Leonid Zhukov},
title = {An {SVD} Based Term Suggestion and Ranking System},
booktitle = {ICDM '04: Proceedings of the Fourth IEEE International Conference
on Data Mining (ICDM'04)},
year = {2004},
pages = {391--394},
address = {Brighton, UK},
month = {November},
publisher = {IEEE Computer Society},
abstract = {In this paper, we consider the application of the singular value decomposition
(SVD) to a search term suggestion system in a pay-for-performance
search market. We propose a novel positive and negative refinement
method based on orthogonal subspace projections. We demonstrate that
SVD subspace-based methods: 1) expand coverage by reordering the
results, and 2) enhance the clustered structure of the data. The
numerical experiments reported in this paper were performed on Overture's
pay-per-performance search market data.},
doi = {10.1109/ICDM.2004.10006},
file = {:gleich 2004 - svd based term suggestion and ranking.pdf:PDF},
isbn = {0-7695-2142-8},
key = {GZ2004},
keywords = {self},
owner = {David Gleich},
timestamp = {2006.10.13}
}
@inproceedings{gleich2005-wom,
author = {David F. Gleich and Leonid Zhukov and Matthew Rasmussen and Kevin
Lang},
title = {The {World of Music}: {SDP} Embedding of High Dimensional data},
booktitle = {Information Visualization 2005},
year = {2005},
note = {Interactive Poster},
abstract = {In this paper we investigate the use of Semidefinite Programming (SDP)
optimization for high dimensional data layout and graph visualization.
We developed a set of interactive visualization tools and used them
on music artist ratings data from Yahoo!. The computed layout preserves
a natural grouping of the artists and provides visual assistance
for browsing large music collections.},
file = {:gleich2005 - world of music.pdf:PDF},
key = {GZRL2005},
keywords = {self, recommender systems},
owner = {David Gleich},
timestamp = {2006.10.13}
}
@comment{{jabref-meta: groupsversion:3;}}
@comment{{jabref-meta: groupstree:
0 AllEntriesGroup:;
1 ExplicitGroup:keywords\;2\;;
2 KeywordGroup:pagerank\;0\;keywords\;pagerank\;0\;0\;;
2 KeywordGroup:matrix computations\;0\;keywords\;matrix computations\;
0\;0\;;
2 KeywordGroup:regularization\;0\;keywords\;regularization\;0\;0\;;
2 KeywordGroup:optimization\;0\;keywords\;optimization\;0\;0\;;
2 KeywordGroup:networks\;0\;keywords\;networks\;0\;0\;;
2 KeywordGroup:least squares\;0\;keywords\;least squares\;0\;0\;;
2 KeywordGroup:drazin\;0\;keywords\;drazin\;0\;0\;;
2 KeywordGroup:self\;0\;keywords\;self\;0\;0\;;
2 KeywordGroup:nmf\;0\;keywords\;nmf\;0\;0\;;
1 KeywordGroup:Self Publications\;0\;keywords\;self\;0\;0\;;
1 ExplicitGroup:Graph eigenvalues\;0\;Alon-2010-4-cycles\;Anderson-198
5-Laplacian\;Banerjee-2007-Protein-Protein\;Banerjee-2007-spectral-plo
ts\;Banerjee-2008-normalized-Laplacian\;Banerjee-2008-spectral-classif
ication\;Banerjee-2008-thesis\;Banerjee-2009-graph-spectra\;Banerjee-2
009-spectral-characterization\;Bauer-2001-spectral-moments\;Butler-200
7-Laplacian-interlacing\;Butler-2008-thesis\;Chung-2003-Eigenvalues\;C
hung-2003-Spectra\;Comellas-2005-star-model\;Comellas-2008-spectral-re
construction\;Elasser-2006-eigenvalue-power-law\;Fay:-2010-spectral-di
stribution\;Fiedler1973-algebraic-connectivity\;Fisher-1966-drum\;Flax
man-2005-preferential-attachment-eigenvalues\;Frangioni2001-graph-spec
tra\;Jamakovic-2008-complex-networks\;Merris-1998-Laplacian-eigenvalue
s\;Mihail-2002-eigenvalue-power-law\;Shcherbina2010-eigenvalue\;Wilson
-2008-spectra\;Zlastic-2010-\;;
1 ExplicitGroup:PageRank\;0\;Archak2010-adfactors\;Bar-Yossef2008-reve
rse-PageRank\;Desikan2005-incremental-pagerank\;Ding2009-PageRank-auth
ors\;Shepelyansky2010-Ulam\;deJager2009-pagerank\;;
1 ExplicitGroup:Entity Resolution\;0\;Bhattacharya2006-entity\;Pasula2
002-identity-uncertainty\;;
1 ExplicitGroup:Random Walk Matrix Computations\;0\;Dreitlein1989-stoc
hastic\;Edmundson1953-random-walks\;Halton1962-sequential\;Mascagni200
3-monte-carlo-eigenpair\;Srinivasan2002-Fiedler\;Wasow1952-random-walk
\;;
}}