Objectif Similarity search is the task of identifying, in a collection of items, the ones that are “similar” to a givenquery item. This task has a range of important applications (e.g. in information retrieval, patternrecognition, statistics, and machine learning) where data sets are often big, high dimensional, andpossibly noisy. State-of-the-art methods for similarity search offer only weak guarantees when faced withbig data. Either the space overhead is excessive (1000s of times larger than the space for the data itself),or the work needed to report the similar items may be comparable to the work needed to go through allitems (even if just a tiny fraction of the items are similar). As a result, many applications have to resort tothe use of ad-hoc solutions with only weak theoretical guarantees.This proposal aims at strengthening the theoretical foundation of scalable similarity search, anddeveloping novel practical similarity search methods backed by theory. In particular we will:- Leverage new types of embeddings that are kernelized, asymmetric, and complex-valued.- Consider statistical models of noise in data, and design similarity search data structures whoseperformance guarantees are phrased in statistical terms.- Build a new theory of the communication complexity of distributed, dynamic similarity search,emphasizing the communication bottleneck present in modern computing infrastructures.The objective is to produce new methods for similarity search that are: 1) Provably robust, 2) scalableto large and high-dimensional data sets, 3) substantially more resource efficient than current state-ofthe-art solutions, and 4) able to provide statistical guarantees on query answers.The study of similarity search has been an incubator for techniques (e.g. locality-sensitive hashing andrandom projections) that have wide-ranging applications. The new techniques developed in this projectare likely to have significant impacts beyond similarity search. Champ scientifique natural sciencescomputer and information sciencesdata sciencebig datanatural sciencescomputer and information sciencesartificial intelligencepattern recognitionnatural sciencesmathematicsapplied mathematicsstatistics and probabilitynatural sciencescomputer and information sciencesartificial intelligencemachine learning Programme(s) FP7-IDEAS-ERC - Specific programme: "Ideas" implementing the Seventh Framework Programme of the European Community for research, technological development and demonstration activities (2007 to 2013) Thème(s) ERC-CG-2013-PE6 - ERC Consolidator Grant - Computer Science and Informatics Appel à propositions ERC-2013-CoG Voir d’autres projets de cet appel Régime de financement ERC-CG - ERC Consolidator Grants Institution d’accueil IT-UNIVERSITETET I KOBENHAVN Contribution de l’UE € 1 889 711,73 Adresse RUED LANGGAARDSVEJ 7 2300 Kobenhavn Danemark Voir sur la carte Région Danmark Hovedstaden Byen København Type d’activité Higher or Secondary Education Establishments Contact administratif Georg Dam Steffensen (Mr.) Chercheur principal Rasmus Pagh (Dr.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée Bénéficiaires (1) Trier par ordre alphabétique Trier par contribution de l’UE Tout développer Tout réduire IT-UNIVERSITETET I KOBENHAVN Danemark Contribution de l’UE € 1 889 711,73 Adresse RUED LANGGAARDSVEJ 7 2300 Kobenhavn Voir sur la carte Région Danmark Hovedstaden Byen København Type d’activité Higher or Secondary Education Establishments Contact administratif Georg Dam Steffensen (Mr.) Chercheur principal Rasmus Pagh (Dr.) Liens Contacter l’organisation Opens in new window Site web Opens in new window Coût total Aucune donnée