Patents by Inventor Ciarán M. Gilligan-Lee

Ciarán M. Gilligan-Lee has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • CONTRASTIVE EMBEDDING OF STRUCTURED SPACE FOR BAYESIAN OPTIMIZATION
    Publication number: 20240119279
    Abstract: Contrastive learning is used to learn an alternative embedding. A subtree replacement strategy generates structurally similar pairs of samples from an input space for use in contrastive learning. The resulting embedding captures more of the structural proximity relationships of the input space and improves Bayesian optimization performance when applied to tasks such as fitting and optimization.
    Type: Application
    Filed: November 16, 2022
    Publication date: April 11, 2024
    Applicant: Spotify AB
    Inventors: Zhenwen Dai, Ciarán M. Gilligan-Lee, Josh C. Tingey