Skip to content

Error in BPR loss function #185

@PeterZaidel

Description

@PeterZaidel

Hello! Thank you for your great work!
In your realisation of bpr loss you use the following formula:

loss = (1.0 - torch.sigmoid(positive_predictions - negative_predictions)).

In the original publication (bpr paper) the authors propose
loss = log(sigmoid(positive - negative)) + regularisation.
Is it okay?

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