Skip to content

Covariance loss is different from paper #20

Description

@dltkddn0525

Hi,
Thanks for great research. However, it seems that covariance loss is implemented different from the description in your paper.
(https://github.com/changun/CollMetric/blob/master/CML.py#L174) According to your paper, covariance loss is defined as 1/N(||C||_f - ||diag(C)||_2^2), where C is a covariance matrix between all pairs of dimensions. But you implemented it as summation of off-diagonal elements of covariance matrix, which may result in negative scale. Could you provide some more explanation about covariance loss?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions