Accelerating Large-Scale Inference with Anisotropic Vector Quantization
Jul 12, 2020
Speakers
Philip Sun
Řečník · 2 sledující
Erik Lindgren
Řečník · 0 sledujících
David Simcha
Řečník · 0 sledujících
Felix Chern
Řečník · 0 sledujících
Sanjiv Kumar
Řečník · 2 sledující
About
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 achieves state-of-the-art results on the public benchmarks available at <ann-benchmarks.com>.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…
Categories
Vývoj webu a UX/UI
Kategorie · 1,2k prezentací
Marketing a obchodní strategie
Kategorie · 1,4k prezentací
Umělá inteligence a data science
Kategorie · 10,8k prezentací
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Acceleration for Compressed Gradient Descent in Distributed Optimization
Zhlédnout později
Zhize Li, …
Learning Factorized Weight Matrix for Joint Image Filtering
Zhlédnout později
Xiangyu Xu, …
Evolutionary Reinforcement Learning for Sample-Efficient Multiagent Cooperation
Zhlédnout později
Graph Neural Networks for Self-Driving
Zhlédnout později
