Leello Tadesse Dadi reposted
I've noticed there is some confusion about Dion since it mathematically looks so different from Muon and Spectral descent, so I wrote a small note expressing Dion in terms of the SVD and how it differs from PowerSGD 👇
Leello Tadesse Dadi reposted
Hyperplane projections are really powerful approach and seem to pop up everywhere in optimization. A quick overview which might be interesting to some 👇
Leello Tadesse Dadi reposted
When comparing optimization methods, we often change *multiple things at once*—geometry, normalization, etc.—possibly without realizing it. Let's disentangle these changes. 👇
United States Trends
- 1. CarPlay 3,268 posts
- 2. Osimhen 66.4K posts
- 3. Cynthia 98.7K posts
- 4. Megyn Kelly 16.6K posts
- 5. Senator Fetterman 8,957 posts
- 6. Katie Couric 7,047 posts
- 7. Padres 27.6K posts
- 8. Black Mirror 4,145 posts
- 9. #WorldKindnessDay 15K posts
- 10. Gabon 108K posts
- 11. Vine 16K posts
- 12. Woody Johnson N/A
- 13. #LoveDesignEP7 201K posts
- 14. RIN AOKBAB BEGIN AGAIN 200K posts
- 15. #NGAGAB 14.3K posts
- 16. Sheel N/A
- 17. Massie 97.8K posts
- 18. Bonhoeffer 3,686 posts
- 19. ariana 84.2K posts
- 20. Tommy James N/A
Loading...
Something went wrong.
Something went wrong.