-
Notifications
You must be signed in to change notification settings - Fork 526
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.
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
[FEA] PCA initialization for TSNE #3458
Comments
This issue has been labeled |
Linking #1029 and preferring use of this issue since we have made progress on sparse PCA since the original issue was opened. |
This issue has been labeled |
UMAP uses a spectral embedding to initialize points and it was recently demonstrated in this paper that the choice of initialization is important to preserving global structure. The paper also demonstrates that TSNE can preserve global structure fairly well by using PCA to initialize the embeddings.
The PCA initialization is done directly on the training data (using only the first 2 principal components).
The text was updated successfully, but these errors were encountered: