Xiang M Wu

20210064634, Mar 4, 2021

Aug 25, 2020

17/001850

- Mountain View CA, US
David Simcha - Jersey City NJ, US
Quan Geng - Jersey City NJ, US
Felix Chern - New York NY, US
Sanjiv Kumar - Jericho NY, US
Xiang Wu - Berkeley CA, US

G06F 16/25
G06F 16/2457
H03M 7/30

Generally, the present disclosure is directed to systems and methods of quantizing a database with respect to a novel loss or quantization error function which applies a weight to an error measurement of quantized elements respectively corresponding to the datapoints in the database. The weight is determined based on the magnitude of an inner product between the respective datapoints and a query compared therewith. In contrast to previous work, embodiments of the proposed loss function are responsive to the expected magnitude of an inner product between the respective datapoints and a query compared therewith and can prioritize error reduction for higher-ranked pairings of the query and the datapoints. Thus, the systems and methods of the present disclosure provide solutions to some of the problems with traditional quantization approaches, which regard all error as equally impactful.