References.bib

@article{Aggarwal,
	author = "Charu Aggarwal and Alexander Hinneburg and Daniel Keim",
	title = "On the Surprising Behavior of Distance Metrics in High Dimensional Space"
}

@article{Andersen,
	author = "Bin Fan and David Andersen and Michael Kamisnku and Michael Mitzenmacher",
	title = "Cuckoo Filter: Practically Better Than Bloom",
}
	
@online{Arthur,
	author = "David Arthur and Sergei Vassilvitskii",
	title = "The Advantages of Careful Seeding"
}
@article{Achlioptas,
	author = "Dimitris Achlioptas",
	title = "Database friendly random projections Johnson-Lindestrauss with Binary Coins"
}

@article{Alon,
	author = "Noga Alon and Yossi Matias and Mario Szegedy",
	title = "The space complexity of approximating the frequency moments"
}

@article{Andoni,
	author = "Alexandr Andoni and Piotr Indyk and Thijs Laarhoven and Ilya Razenshteyn",
	title = "Beyond Locality Sensitive Hashing"
}

@article{Andoni2,
	author = "Alexandr Andoni and Piotr Indyk and Thijs Laarhoven and Ilya Razenshteyn",
	title = "Practical and Optimal LSH for Angular Distance"
}

@article{Attenberg,
	author = "Joshua Attenberg and Killian Weinberger",
	title = "Collaborative Email Spam Filtering with the Hashing Trick"
}


@Article{Babenko,
 	 author="Artem Babenko and Victor Lempitsky",
 	 title="The Inverted Multi Index"
}

@Article{Bahmani,
	author="Bahman Bahmani and Benjamin Mosley and Andrea Vattani and Ravi Kumar and Sergei Vassilvistkii",
	title="Scalable Kmeans plus plus"
}


@Article{Banko,
	author="Michele Banko and Eric Brill",
	year=2001,
	title="Scaling to Very Very Large Corpora forNatural Language Disambiguation"
}

@article{Bawa,
 	 author="Mayank Bawa and Tyson Condie and Prasanna Ganesan",
	 title="LSH Forest Self Tuning Indexes for Similarity Search"
}


@article{Belazzougui,
 	 author="Djamal Belazzougui and Fabiano Botelho and Martin Dietzfelbinger",
	 title="Hash Displace and Compress"
}

@article{Belkin,
 	 author="Mikhail Belkin and Partha Niyogi",
	 title="Laplacian Eigenmaps for Dimensionality Reduction and Data Representation"
}


@article{Beyer,
 	 author="Beyer K. and Goldstein J. and Ramakrishnan R. and Shaft U",
	 title="When is Nearest Neighbors Meaningful?"
}

@article{BotelhoPaghZiviani,
 	 author="Fabiano Botelho and Rasmus Pagh and Nivio Ziviani",
	 title="Simple and Space Efficient Minimal Perfect Hash Functions"
}


@article{BottouBengio,
 	 author="Leon Bottoul and and Yoshua Bengio",
	 title="Convergence Properties of the K-Means Algorithms"
}

@article{BurrowsWheeler,
 	 author="M. Burrows and David J Wheeler",
	 title="A block-sorting lossless data compression algorithm"
}

@article{CampelloMoulaviSander,
 	 author="Ricardo J. G. B. Campello and Davoud Moulavi and Joerg Sander",
	 title="Density Based Clustering Based on Hierarchical Density Estimates"
}

@article{Carlson,
 	 author="Gunnar Carlson",
	 title="Topology and Data"
}

@article{Charalampos,
 	 author="Charalampos and Tsourakakis",
	 title="Fast Counting of Triangles in Large Real Networks"
}


@article{Charikar,
 	 author="M Charikar",
	 title="Similarity Estimation Techniques from Rounding Algorithms"
}

@article{Chazelle,
 	 author="Bernard Chazelle and Nor Ailon",
	 title="Approximate Nearest Neighbors and the Fast Johnson-Lindenstrauss Transform"
}

@article{ChenGuestrin,
 	 author="Tianqi Chen and Carlos Guestin",
	 title="XGBoost: A Scalable Tree Boosting System"
}

@article{ClausetNewmanMoore,
 	 author="Aaron Clauset and M. E. J. Newman and Cristopher Moore",
	 title="Finding community structure in very large networks"
}

@article{ClearlyWitten,
 	 author="Cleary and J. and Witten I.",
	 title="Data Compression Using Adaptive Coding and Partial String Matching",
}

@article{CormackHorspool,
 	 author="Gordon Cormack and Nigel Horspool",
	 title="Data Compression using Dynamic Markov Modelling"
}

@article{Dasgupta,
 	 author="Sanjoy Dasgupta and Anupam Gupta",
	 title="An elementary proof of the Johnson-Lindenstrauss Lemma"
}

@article{DatarGionisIndykMotwani,
 	 author="M. Datar and A Gionis and P Indyk and R. Motwani",
	 title="Maintaining stream statistics over sliding windows"
}

@article{Dean,
 	 author="Jeffrey Dean and Sanjay Ghemawat",
	 title="MapReduce: Simplified Data Processing on Large Clusters"
}

@article{Dhillon,
	author="Inderjit S Dhillon",
	title="Co-clustering documents and words using bipartite spectral graph partitioning"
}


@article{Dietzfelbinger,
 	 author="M. Dietzfelbinger and A. Karlin and K. Mehlhorn and F. Meyer auf der Heide and H. Rohnert and R. E. Tarjan",
	 title="Dynamic perfect hashing upper and lower bounds"
}

@article{Dimitropoulos,
 	 author="Xenofontas Dimitropoulos and Marc Stoecklin and Paul Hurley and Andreas Kind",
	 title="The Eternal Sunshine of the Sketch Data Structure"
}


@article{Dong,
 	 author="Wei Dong and Moses Charikar and Kai Li. (2011)",
	 title="Efficient K-Nearest Neighbor Graph Construction for Generic Similarity Measures"
}
 
@Article{Eldridge,
 	 author="Justin Eldridge and Mikhail Belkin",
	 title="Beyond Hartigan Consistency Merge Distortion Metric for Hierarchical Clustering"
}

@article{FlajoletMartin,
 	 author="Philippe Flajolet and Nigel Martin",
	 title="Probabilistic Counting Algorithms for Data Base Applications"
}

@article{Flajolet,
 	 author="Philippe Flajolet and Eric Fusy and Olivier Gandouet and Frederic Meunier",
	 title="The analysis of a near-optimal cardinality estimation algorithm"
}

@article{FredmanKomlosSzemeredi,
 	 author="Michael Fredman and Janos Komlos and Endre Szemeredi",
	 title="Storing a Sparse Table with O(1) Worst Case Access Time"
}

@article{GoodMontjoyeClauset,
 	 author="Good and Montjoye and Aaron Clauset",
	 title="The performance of modularity maximization in practical contexts"
}

@article{Gou,
 	 author="Janping Gou and Lan Du and Yuhong Zhang and Taisong Xiong. (2012)",
	 title="A New Distance-weighted k-nearest Neighbor Classifier"
}

@article{Grumwald,
 	 author="Peter Grumwald",
	 title="A Tutorial Introduction to the Minimum Description Length Principle"
}

@article{GuhaRastogiShim,
 	 author="Guha and Sudipto and Rastogi and Rajeev and Shim and Kyuseok",
	 title="CURE An Efficient Clustering Algorithm for Large Databases"
}

@article{Hajebi,
 	 author="Kiana Hajebi and Yasin Abbasi-Yadkori and Hossein Shahbazi and Hong Zhang",
	 title="Fast Approximate Nearest-Neighbor Search with k-Nearest Neighbor Graph"
}

@article{Houle,
 	 author="Michael E. Houle and Hans-Peter Kriegel and Peer Kroger and Erich Schubert and Arthur Zimek",
	 title="Can Shared-Neighbor Distances Defeat the Curse of Dimensionality?"
}

@article{IndykMotwani,
 	 author="Piotr Indyk and Rajeev Motwani and Aristides Gionis",
	 title="Similarity Search in High Dimensions vis Hashing"
}

@article{IndykAndoni,
 	 author="Piotr Indyk and Alexandr Andoni",
	 title="Near Optimal Hashing Algorithms for Approximate Nearest Neigbor in High Dimensions"
}

@article{KalantidisAvrithis,
 	 author="Yannis Kalantidis and Yannis Avrithis",
	 title="Locally Optimized Product Quantization for Approximate Nearest Neighbor Search"
}


@article{KangMeederFaloutsos,
 	 author="U Kang and Brendan Meeder and Christos Faloutsos",
	 title="Spectral Analysis for Billion Scale Graphs Discoveries and Implementation"
}

@article{Karger,
 	 author="David Karger and Eric Lehman and Tom Leighton and Matthew Levine and Daniel Lewin and Rina Panigrahy",
	 title="Consistent Hashing and Random Trees:Distributed Caching Protocols for Relieving Hot Spots on the World Wide Web"
}

@article{Kennedy,
 	 author="Cristopher Kennedy and Rachel Ward",
	 title="Fast Cross Polytope LSH"
}


@article{Kleinberg,
 	 author="Jon Kleinberg",
	 title="Authoritative sources in a hyperlinked environment"
}

@article{KnolldeFreitas,
 	 author="Byron Knoll and Nando de Freitas",
	 title="A Machine Learning Perspective on Predictive Coding with PAQ"
}

@article{Koren,
 	 author="Yehuda Koren",
	 title="Factorization Meets the Neighborhood"
}

@article{Lemire,
 	 author="D. Lemire and G. Ssi-Yan-Kai and O. Kaser",
	 title="Consistently faster and smaller compressed bitmaps with Roaring"
}

@article{LempelZivC,
 	 author="Lempel and A. and Ziv and J",
	 title="On the complexity of finite sequences"
}

@article{Leskovec,
 	 author="J Yang and Jure Leskovec",
	 title="Overlapping Community Detection at Scale A Nonnegative Matrix Factorization Approach"
}

@article{Louvain,
 	 author="Vincent D Blondel and Jean-Loup Guillaume and Renaud Lambiotte and Etienne Lefebvre",
	 title="Fast unfolding of communities in large networks"
}

@article{MuthukrishnanCormode,
 	 author="S. Muthukrishnan and Graham Cormode",
	 title="The Count-Min Sketch and its Applications"
}

@article{PageBrin,
 	 author="Larry Page and Sergey Brin",
	 title="The PageRank Citation Ranking Bringing Order to the Web"
}

@article{ParkLeckie,
 	 author="Laurence A F Park and Christopher A Leckie and Kotagiri Ramamohanarao and James C Bezdek",
	 title="Adapting spectral coclustering to documents and terms using latent semantic analysis"
}

@article{Rendle,
 	 author="Steffen Rendle",
	 title="Factorization Machines"
}

@article{Rendle2,
 	 author="Steffen Rendle",
	 title="Factorization Machines with LibFM"
}

@article{Rissanen,
 	 author="Rissanen and J",
	 title="Modeling by the shortest data description"
}

@article{RosvallBergstrom,
 	 author="Martin Rosvall and Carl T Bergstrom",
	 title="Maps of random walks on complex networks reveal community structure"
}

@article{Pagh,
 	 author="Rasmus Pagh",
	 title="Hash and Displace Efficient Evaluation of Minimal Perfect Hash Functions"
}

@article{PaghRodler,
 	 author="Rasmus Pagh and Flemming Rodler",
	 title="Cuckoo Hashing"
}

@article{Shannon,
 	 author="Shannon Claude",
	 title="A Mathematical Theory of Communication"
}

@article{Shi,
 	 author="Qinfeng Shi and James Petterson and John Langford and Alex Smola and Alex Strehl and Gideon Dror and Vishy Vishwanathan",
	 title="Hash Kernels"
}

@article{Shi2,
 	 author="Qinfeng Shi and James Petterson and John Langford and Alex Smola and Alex Strehl and Gideon Dror and Vishy Vishwanathan",
	 title="Hash Kernels for Structured Data"
}

@article{SinghMemoliCarlson,
 	 author="Gruheet Singh and Facundo Memoli and Gunnar Carlson",
	 title="Topological Methods for the Analysis of High Dimensional Data Sets and 3D Object Recognition"
}

@article{SwamidassBaldi,
 	 author="S Joshua Swamidass and Pierre Baldi",
	 title="Bounds and algorithms for fast exact searches of chemical fingerprints in linear and sublinear time"
}

@article{Ugander,
 	 author="Johan Ugander and Brian Karrer and Lars Backstrom and Cameron Marlow",
	 title="The Anatomy of the Facebook Social Graph"
}

@article{Valiant,
 	 author="Leslie Valiant",
	 title="A Theory of the Learnable"
}

@article{vanDerMaatenHinton,
 	 author="Laurens van der Maaten and Geoffrey Hinton",
	 title="Visualizing Data using t-SNE"
}

@article{vanDerMaaten,
 	 author="Laurens van der Maaten",
	 title="Learning a Parametric Embedding by Preserving Local Structure"
}

@article{Vitanyi,
 	 author="Rudi Cilibrasi and Paul M.B. Vitanyi",
	 title="Clustering by Compression"
}

@article{Ward,
 	 author="J.H Ward Jr",
	 title="Hierarchical Grouping to Optimize an Objective Function"
}

@article{Weinberger,
 	 author="Killian Weinberger and Anirban Dasgupta and John Langford and Alex Smola and Josh Attenberg",
	 title="Feature Hashing for Large Scale Multitask Learning"
}

@article{WeissNgJordan,
 	 author="Yair Weiss and Andrew Ng and Michael Jordan",
	 title="On Spectral Clustering Analysis and Algorithm"
}

@article{Wickham,
 	 author="Hadley Wickham. (2004)",
	 title="Tidy Data"
} 

@article{WittenBell,
 	 author="I.H. Witten and T.C. Bell",
	 title="The zero-frequency problem: estimating the probabilities of novel events in adaptive text compression"
}

@article{Wolpert,
 	 author="D.H. Wolpert and W.G. Macready",
	 title="No Free Lunch Theorems for Optimization"
}

@article{YanHuangJordan,
 	 author="Donghui Yan and Lin Huang and Michael Jordan",
	 title="Fast Approximate Spectral Clustering"
}

@article{Zhang,
 	 author="Jing Zhang and Jie Tang and Cong Ma and Hanghang Tong and Yu Jing and Juanzi Li",
	 title="Panther Fast Top K Similarity Search in Large Networks"
}


@article{ZhouLiAndersenSmola,
 	 author="Li Zhou and Mu Li and David Andersen and Alexander Smola",
	 title="Cuckoo Linear Algebra"
}