US 11,675,855 B2
Variable thresholds in constrained optimization
Anton Zhernov, London (GB); Krishnamurthy Dvijotham, London (GB); Xiaohong Gong, Sunnyvale, CA (US); and Amogh S. Asgekar, Palo Alto, CA (US)
Assigned to DeepMind Technologies Limited, London (GB)
Filed by DeepMind Technologies Limited, London (GB)
Filed on Nov. 18, 2020, as Appl. No. 16/951,920.
Claims priority of provisional application 62/937,226, filed on Nov. 18, 2019.
Prior Publication US 2021/0149968 A1, May 20, 2021
Int. Cl. G06F 17/00 (2019.01); G06F 16/93 (2019.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01)
CPC G06F 16/93 (2019.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a request to re-rank a first collection of documents according to a first metric and subject to a constraint on a function of one or more second metrics;
obtaining, for each document in the first collection of documents, a respective first metric value corresponding to the first metric and respective one or more second metric values corresponding to the one or more second metrics;
in response to the request to re-rank the first collection of documents, re-ranking the first collection of documents, comprising:
determining the constraint on the function of one or more second metrics by computing a first threshold value using a variable threshold function that takes as input second metric values for the documents in the first collection of documents; and
determining the re-ranking for the first collection of documents by solving a constrained optimization for the first metric constrained by the first threshold value for the function of one or more second metrics, and
providing data representing the re-ranked first collection of documents to a device for display.