Work

AÇAI: Ascent Similarity Caching with Approximate Indexes

Year: 2021

Type: conference-paper

Abstract: Similarity search is a key operation in multimedia retrieval systems and recommender systems, and it will play an important role also for future machine learning and augmented reality applications. When these systems need to serve large objects with tight delay constraints, edge servers close to the end-user can operate as similarity caches to speed up the retrieval. In this paper we present AÇAI, a new similarity caching policy which improves on the state of the art by using (i) an (approximate) index for the whole catalog to decide which objects to serve locally and which to retrieve from the remote server, and (ii) a mirror ascent algorithm to update the set of local objects with strong guarantees even when the request process does not exhibit any statistical regularity.

Source: HAL

Authors: Si Salem, Tareq, Neglia, Giovanni, Carra, Damiano

Institutions: Université Côte d'Azur, NEO: Ingénierie et Opérations des Réseaux, University of Verona

Language: English

Topic: Algorithms and Data Compression

Subfield: Theoretical Computer Science

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3182377036

FWCI: 1.131

Cites: 49

Cited by: 4

Related to: 10