Results 1  10
of
348
Nearoptimal hashing algorithms for approximate nearest neighbor in high dimensions
, 2008
"... In this article, we give an overview of efficient algorithms for the approximate and exact nearest neighbor problem. The goal is to preprocess a dataset of objects (e.g., images) so that later, given a new query object, one can quickly return the dataset object that is most similar to the query. The ..."
Abstract

Cited by 235 (4 self)
 Add to MetaCart
In this article, we give an overview of efficient algorithms for the approximate and exact nearest neighbor problem. The goal is to preprocess a dataset of objects (e.g., images) so that later, given a new query object, one can quickly return the dataset object that is most similar to the query. The problem is of significant interest in a wide variety of areas.
Finding motifs using random projections
, 2001
"... Pevzner and Sze [23] considered a precise version of the motif discovery problem and simultaneously issued an algorithmic challenge: find a motif Å of length 15, where each planted instance differs from Å in 4 positions. Whereas previous algorithms all failed to solve this (15,4)motif problem, Pevz ..."
Abstract

Cited by 210 (5 self)
 Add to MetaCart
Pevzner and Sze [23] considered a precise version of the motif discovery problem and simultaneously issued an algorithmic challenge: find a motif Å of length 15, where each planted instance differs from Å in 4 positions. Whereas previous algorithms all failed to solve this (15,4)motif problem, Pevzner and Sze introduced algorithms that succeeded. However, their algorithms failed to solve the considerably more difficult (14,4), (16,5), and (18,6)motif problems. We introduce a novel motif discovery algorithm based on the use of random projections of the input’s substrings. Experiments on simulated data demonstrate that this algorithm performs better than existing algorithms and, in particular, typically solves the difficult (14,4), (16,5), and (18,6)motif problems quite efficiently. A probabilistic estimate shows that the small values of � for which the algorithm fails to recover the planted Ð � �motif are in all likelihood inherently impossible to solve. We also present experimental results on realistic biological data by identifying ribosome binding sites in prokaryotes as well as a number of known transcriptional regulatory motifs in eukaryotes. 1. CHALLENGING MOTIF PROBLEMS Pevzner and Sze [23] considered a very precise version of the motif discovery problem of computational biology, which had also been considered by Sagot [26]. Based on this formulation, they issued an algorithmic challenge: Planted Ð � �Motif Problem: Suppose there is a fixed but unknown nucleotide sequence Å (the motif) of length Ð. The problem is to determine Å, givenØ nucleotide sequences each of length Ò, and each containing a planted variant of Å. More precisely, each such planted variant is a substring that is Å with exactly � point substitutions. One instantiation that they labeled “The Challenge Problem ” was parameterized as finding a planted (15,4)motif in Ø � sequences each of length Ò � �. These values of Ò, Ø, andÐ are
Sparse Greedy Matrix Approximation for Machine Learning
, 2000
"... In kernel based methods such as Regularization Networks large datasets pose signi cant problems since the number of basis functions required for an optimal solution equals the number of samples. We present a sparse greedy approximation technique to construct a compressed representation of the ..."
Abstract

Cited by 177 (11 self)
 Add to MetaCart
In kernel based methods such as Regularization Networks large datasets pose signi cant problems since the number of basis functions required for an optimal solution equals the number of samples. We present a sparse greedy approximation technique to construct a compressed representation of the design matrix. Experimental results are given and connections to KernelPCA, Sparse Kernel Feature Analysis, and Matching Pursuit are pointed out. 1. Introduction Many recent advances in machine learning such as Support Vector Machines [Vapnik, 1995], Regularization Networks [Girosi et al., 1995], or Gaussian Processes [Williams, 1998] are based on kernel methods. Given an msample f(x 1 ; y 1 ); : : : ; (x m ; y m )g of patterns x i 2 X and target values y i 2 Y these algorithms minimize the regularized risk functional min f2H R reg [f ] = 1 m m X i=1 c(x i ; y i ; f(x i )) + 2 kfk 2 H : (1) Here H denotes a reproducing kernel Hilbert space (RKHS) [Aronszajn, 1950],...
Discovering similar multidimensional trajectories
 In ICDE
, 2002
"... We investigate techniques for analysis and retrieval of object trajectories in a two or three dimensional space. Such kind of data usually contain a great amount of noise, that makes all previously used metrics fail. Therefore, here we formalize nonmetric similarity functions based on the Longest C ..."
Abstract

Cited by 171 (6 self)
 Add to MetaCart
We investigate techniques for analysis and retrieval of object trajectories in a two or three dimensional space. Such kind of data usually contain a great amount of noise, that makes all previously used metrics fail. Therefore, here we formalize nonmetric similarity functions based on the Longest Common Subsequence (LCSS), which are very robust to noise and furthermore provide an intuitive notion of similarity between trajectories by giving more weight to the similar portions of the sequences. Stretching of sequences in time is allowed, as well as global translating of the sequences in space. Efficient approximate algorithms that compute these similarity measures are also provided. We compare these new methods to the widely used Euclidean and Time Warping distance functions (for real and synthetic data) and show the superiority of our approach, especially under the strong presence of noise. We prove a weaker version of the triangle inequality and employ it in an indexing structure to answer nearest neighbor queries. Finally, we present experimental results that validate the accuracy and efficiency of our approach. 1
Finding interesting associations without support pruning
 In ICDE
, 2000
"... Abstract Associationrule mining has heretofore relied on the condition of high support to do its work efficiently. In particular, the wellknown apriori algorithm is only effective when the only rules of interest are relationships that occur very frequently. However, there are a number of applicat ..."
Abstract

Cited by 136 (15 self)
 Add to MetaCart
Abstract Associationrule mining has heretofore relied on the condition of high support to do its work efficiently. In particular, the wellknown apriori algorithm is only effective when the only rules of interest are relationships that occur very frequently. However, there are a number of applications, such as data mining, identification of similar web documents, clustering, and collaborative filtering, where the rules of interest have comparatively few instances in the data. In these cases, we must look for highly correlated items, or possibly even causal relationships between infrequent items. We develop a family of algorithms for solving this problem, employing a combination of random sampling and hashing techniques. We provide analysis of the algorithms developed, and conduct experiments on real and synthetic data to obtain a comparative performance analysis.
Google news personalization: scalable online collaborative filtering
 in WWW, 2007
"... Several approaches to collaborative filtering have been studied but seldom have studies been reported for large (several million users and items) and dynamic (the underlying item set is continually changing) settings. In this paper we describe our approach to collaborative filtering for generating p ..."
Abstract

Cited by 131 (0 self)
 Add to MetaCart
Several approaches to collaborative filtering have been studied but seldom have studies been reported for large (several million users and items) and dynamic (the underlying item set is continually changing) settings. In this paper we describe our approach to collaborative filtering for generating personalized recommendations for users of Google News. We generate recommendations using three approaches: collaborative filtering using MinHash clustering, Probabilistic Latent Semantic Indexing (PLSI), and covisitation counts. We combine recommendations from different algorithms using a linear model. Our approach is content agnostic and consequently domain independent, making it easily adaptable for other applications and languages with minimal effort. This paper will describe our algorithms and system setup in detail, and report results of running the recommendations engine on Google News.
Efficient Similarity Search and Classification Via Rank Aggregation
 In Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data
, 2003
"... We propose a novel approach to performing efficient similarity search and classification in high dimensional data. In this framework, the database elements are vectors in a Euclidean space. Given a query vector in the same space, the goal is to find elements of the database that are similar to the ..."
Abstract

Cited by 122 (5 self)
 Add to MetaCart
We propose a novel approach to performing efficient similarity search and classification in high dimensional data. In this framework, the database elements are vectors in a Euclidean space. Given a query vector in the same space, the goal is to find elements of the database that are similar to the query. In our approach, a small number of independent "voters" rank the database elements based on similarity to the query. These rankings are then combined by a highly efficient aggregation algorithm. Our methodology leads both to techniques for computing approximate nearest neighbors and to a conceptually rich alternative to nearest neighbors.
Multidimensional range queries in sensor networks
 in Proc. of the 1st international conference on Embedded networked sensor systems, SenSys
"... In many sensor networks, data or events are named by attributes. Many of these attributes have scalar values, so one natural way to query events of interest is to use a multidimensional range query. An example is: “List all events whose temperature lies between 50 ◦ and 60 ◦ , and whose light levels ..."
Abstract

Cited by 121 (11 self)
 Add to MetaCart
In many sensor networks, data or events are named by attributes. Many of these attributes have scalar values, so one natural way to query events of interest is to use a multidimensional range query. An example is: “List all events whose temperature lies between 50 ◦ and 60 ◦ , and whose light levels lie between 10 and 15. ” Such queries are useful for correlating events occurring within the network. In this paper, we describe the design of a distributed index that scalably supports multidimensional range queries. Our distributed index for multidimensional data (or DIM) uses a novel geographic embedding of a classical index data structure, and is built upon the GPSR geographic routing algorithm. Our analysis reveals that, under reasonable assumptions about query distributions, DIMs scale quite well with network size (both insertion and query costs scale as O ( √ N)). In detailed simulations, we show that in practice, the insertion and query costs of other alternatives are sometimes an order of magnitude more than the costs of DIMs, even for moderately sized network. Finally, experiments on a small scale testbed validate the feasibility of DIMs.
Probabilistic discovery of time series motifs
, 2003
"... Several important time series data mining problems reduce to the core task of finding approximately repeated subsequences in a longer time series. In an earlier work, we formalized the idea of approximately repeated subsequences by introducing the notion of time series motifs. Two limitations of thi ..."
Abstract

Cited by 116 (21 self)
 Add to MetaCart
Several important time series data mining problems reduce to the core task of finding approximately repeated subsequences in a longer time series. In an earlier work, we formalized the idea of approximately repeated subsequences by introducing the notion of time series motifs. Two limitations of this work were the poor scalability of the motif discovery algorithm, and the inability to discover motifs in the presence of noise. Here we address these limitations by introducing a novel algorithm inspired by recent advances in the problem of pattern discovery in biosequences. Our algorithm is probabilistic in nature, but as we show empirically and theoretically, it can find time series motifs with very high probability even in the presence of noise or “don’t care ” symbols. Not only is the algorithm fast, but it is an anytime algorithm, producing likely candidate motifs almost immediately, and gradually improving the quality of results over time.
Fast pose estimation with parameter sensitive hashing
 In ICCV
, 2003
"... Examplebased methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and highdimensional problems such as pose estimation, the number of required examples and the computational complexity rapidly become pro ..."
Abstract

Cited by 102 (4 self)
 Add to MetaCart
Examplebased methods are effective for parameter estimation problems when the underlying system is simple or the dimensionality of the input is low. For complex and highdimensional problems such as pose estimation, the number of required examples and the computational complexity rapidly become prohibitively high. We introduce a new algorithm that learns a set of hashing functions that efficiently index examples relevant to a particular estimation task. Our algorithm extends a recently developed method for localitysensitive hashing, which finds approximate neighbors in time sublinear in the number of examples. This method depends critically on the choice of hash functions; we show how to find the set of hash functions that are optimally relevant to a particular estimation problem. Experiments demonstrate that the resulting algorithm, which we call ParameterSensitive Hashing, can rapidly and accurately estimate the articulated pose of human figures from a large database of example images. 1.