Appears in collection : 2022 - T3 - WS3 - Measure-theoretic Approaches and Optimal Transportation in Statistics

In this work, we consider the question of the optimality of two-sample tests based on MMD. Based on an operator perspective, we propose a spectral regularized two-sample test involving both the mean element and covariance operator and show it to be minimax optimal for a suitable class of alternatives, while the MMD test fails to be optimal. Since the proposed test requires knowledge of the regularization parameter, we propose an adaptive test based on aggregation and show it to be minimax optimal up to logarithmic factors.

Information about the video

Citation data

  • DOI 10.57987/IHP.2022.T3.WS3.010
  • Cite this video Sriperumbudur Bharath (11/24/22). Spectral regularized kernel two-sample tests. IHP. Audiovisual resource. DOI: 10.57987/IHP.2022.T3.WS3.010
  • URL https://dx.doi.org/10.57987/IHP.2022.T3.WS3.010

Domain(s)

Last related questions on MathOverflow

You have to connect your Carmin.tv account with mathoverflow to add question

Ask a question on MathOverflow




Register

  • Bookmark videos
  • Add videos to see later &
    keep your browsing history
  • Comment with the scientific
    community
  • Get notification updates
    for your favorite subjects
Give feedback