Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Optimize categorical crossentropy gradient update #91

Open
NicolasHug opened this issue Feb 4, 2019 · 3 comments
Open

Optimize categorical crossentropy gradient update #91

NicolasHug opened this issue Feb 4, 2019 · 3 comments
Assignees
@NicolasHug
Labels
perf Computational performance issue or improvement

Comments

@NicolasHug
Copy link
Collaborator

The gradient and hessian update of the categorical crossentropy loss computes p_k k times, but it only needs to compute it once (see scikit-learn/scikit-learn@9e68984 which led to serious improvement in fit time).
@NicolasHug NicolasHug added the perf Computational performance issue or improvement label Feb 4, 2019
@NicolasHug NicolasHug self-assigned this Feb 4, 2019
@ogrisel
Copy link
Owner

ogrisel commented Feb 18, 2019

+1 as well.

@aditya1702
Copy link

@NicolasHug Can I also work on this project?

@ogrisel
Copy link
Owner

ogrisel commented Apr 18, 2019

@aditya1702 please feel free to submit a PR.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@NicolasHug NicolasHug

Labels
perf Computational performance issue or improvement
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@ogrisel @NicolasHug @aditya1702