Skip to yearly menu bar Skip to main content


Accelerating Large-Scale Inference with Anisotropic Vector Quantization

Ruiqi Guo · Philip Sun · Erik Lindgren · Quan Geng · David Simcha · Felix Chern · Sanjiv Kumar


Keywords: [ Information Retrieval ] [ Large Scale Learning and Big Data ] [ Recommender Systems ] [ Applications - Other ]


Quantization based techniques are the current state-of-the-art for scaling maximum inner product search to massive databases. Traditional approaches to quantization aim to minimize the reconstruction error of the database points. Based on the observation that for a given query, the database points that have the largest inner products are more relevant, we develop a family of anisotropic quantization loss functions. Under natural statistical assumptions, we show that quantization with these loss functions leads to a new variant of vector quantization that more greatly penalizes the parallel component of a datapoint's residual relative to its orthogonal component. The proposed approach, whose implementation is open-source, achieves state-of-the-art results on the public benchmarks available at

Chat is not available.