Skip to content

Singular fluctuation: Implement more efficient (mini-batched) version #27

@jqhoogland

Description

@jqhoogland

Due to the ordering of gradient descent / sums in the current implementation, we are evaluating losses for the entire dataset instead of minibatching. There might be other algorithms for variance that might be more ameanable to a minibatched estimation approach: https://en.wikipedia.org/wiki/Algorithms_for_calculating_variance

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions