Optimized scalar quantization
AssigneeElastic Technologies (US) Inc.
InventorsBenjamin Whitefield Trent, Thomas James Veasey, John Wagster
Life of this patent
Estimating the term…
Abstract
According to at least one implementation, a method includes receiving a set of vectors from a dataset, where each vector in the set comprises a plurality of dimensions. For a given vector in the set, the method includes determining at least one scaling factor for the plurality of dimensions, iteratively adjusting this scaling factor based on a quantization error to generate at least one optimally adjusted scaling factor, and determining a compressed, quantized vector based on the adjusted scaling factor.
Claims20
A method comprising:
- receiving a set of vectors from a dataset, wherein each vector in the set of vectors comprises a plurality of dimensions;
- and
- for a vector in the set of vectors:
- determining at least one scaling factor for the plurality of dimensions;
- adjusting the at least one scaling factor for the plurality of dimensions based on a quantization error to generate at least one adjusted scaling factor for the plurality of dimensions;
- and
- determining a quantized vector based on the at least one adjusted scaling factor for the plurality of dimensions.
A computer-readable storage medium having program instructions stored thereon that, when executed by at least one processor, direct the at least one processor to perform a method, the method comprising:
- receiving a set of vectors from a dataset, wherein each vector in the set of vectors comprises a plurality of dimensions;
- and
- for a vector in the set of vectors:
- determining at least one scaling factor for the plurality of dimensions;
- adjusting the at least one scaling factor for the plurality of dimensions based on a quantization error to generate at least one adjusted scaling factor for the plurality of dimensions;
- and
- determining a quantized vector based on the at least one adjusted scaling factor for the plurality of dimensions.
A computing system comprising:
- at least one processor;
- a computer-readable storage medium operatively coupled to the at least one processor;
- and
- program instructions stored on the computer-readable storage medium that, when executed by the at least one processor, direct the computing system to perform a method, the method comprising:
- receiving a set of vectors from a dataset, wherein each vector in the set of vectors comprises a plurality of dimensions;
- and
- for a vector in the set of vectors:
- determining at least one scaling factor for the plurality of dimensions;
- adjusting the at least one scaling factor for the plurality of dimensions based on a quantization error to generate at least one adjusted scaling factor for the plurality of dimensions;
- and
- determining a quantized vector based on the at least one adjusted scaling factor for the plurality of dimensions.
Dependencies are inferred from the claim text.