Skip to content

Feature Request: Jacob's Delta-Bar-Delta Update Rule For GradientDescent Optimizer #437

@ranjodhsingh1729

Description

@ranjodhsingh1729

Description

I was trying to implement t-SNE for mlpack and required the delta bar delta update rule given bellow.

Image

I am currently using a callback to achieve the same result. It would be better if this was provided by ensmallen itself.

I can make a PR if there's interest for such a addition.

References

[1] R.A. Jacobs. Increased rates of convergence through learning rate adaptation. Neural
Networks, 1:295–307, 1988.

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