公开(公告)号：US10740328B2

公开(公告)日：2020-08-11

申请号：US15192909

申请日：2016-06-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Bolin Ding ,  Silu Huang ,  Chi Wang ,  Kaushik Chakrabarti ,  Surajit Chaudhuri

IPC: G06F16/2453 ,  G06F16/22 ,  G06F16/2455 ,  G06F16/2458

Abstract: A processing unit can determine a first subset of a data set including data records selected based on measure values thereof. The processing unit can determine an index mapping a predicate to data records associated with that predicate and approximation values of the records. The processing unit can process a query against the first subset to provide a first result and a first accuracy value, determine that the first accuracy value does not satisfy an accuracy criterion, and process the query against the index. In some examples, the processing unit can process the query against a second subset including data records satisfying a predetermined predicate. In some examples, the processing unit can receive data records and determine the first subset. Data records can include respective measure values. Data records with higher measure values can occur in the first subset more frequently than data records with lower measure values.

公开(公告)号：US20170371924A1

公开(公告)日：2017-12-28

申请号：US15192909

申请日：2016-06-24

Applicant: Microsoft Technology Licensing, LLC

Inventor： Bolin Ding ,  Silu Huang ,  Chi Wang ,  Kaushik Chakrabarti ,  Surajit Chaudhuri

IPC: G06F17/30

Abstract: A processing unit can determine a first subset of a data set including data records selected based on measure values thereof. The processing unit can determine an index mapping a predicate to data records associated with that predicate and approximation values of the records. The processing unit can process a query against the first subset to provide a first result and a first accuracy value, determine that the first accuracy value does not satisfy an accuracy criterion, and process the query against the index. In some examples, the processing unit can process the query against a second subset including data records satisfying a predetermined predicate. In some examples, the processing unit can receive data records and determine the first subset. Data records can include respective measure values. Data records with higher measure values can occur in the first subset more frequently than data records with lower measure values.

公开(公告)号：US12223407B2

公开(公告)日：2025-02-11

申请号：US16110419

申请日：2018-08-23

Applicant: Microsoft Technology Licensing, LLC

Inventor： Chi Wang ,  Silu Huang ,  Surajit Chaudhuri ,  Bolin Ding

IPC: G06N20/20 ,  G06F9/445 ,  G06N20/00

Abstract: In automated machine learning, an approximate best configuration can be selected among multiple candidate machine-learning configurations by progressively sampling training and test datasets for the iterative training and testing of the configurations while progressively pruning the set of candidate configurations based on associated estimated confidence intervals for their respective performance.

公开(公告)号：US20200065712A1

公开(公告)日：2020-02-27

申请号：US16110419

申请日：2018-08-23

Applicant: Microsoft Technology Licensing, LLC

Inventor： Chi Wang ,  Silu Huang ,  Surajit Chaudhuri ,  Bolin Ding

IPC: G06N99/00 ,  G06F9/445

Abstract: In automated machine learning, an approximate best configuration can be selected among multiple candidate machine-learning configurations by progressively sampling training and test datasets for the iterative training and testing of the configurations while progressively pruning the set of candidate configurations based on associated estimated confidence intervals for their respective performance.