Ascent Similarity Caching with Approximate Indexes
This work addresses latency issues in edge servers for similarity search applications, offering an incremental improvement over existing caching methods.
The paper tackles the problem of similarity caching for multimedia retrieval and recommender systems under tight delay constraints, presenting AÇAI, a new policy that uses an approximate index and mirror ascent algorithm to improve state-of-the-art performance with strong guarantees for non-stationary request processes.
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.