Keller Jordan @kellerjordan0 · 13 Apr 2023
11/ These findings were obtained from studying standard, well-tuned trainings on CIFAR-10 and ImageNet. As a caveat, for unstable trainings (e.g. too high learning rate) variance exceeds the hypothesis and is certainly not harmless. https://t.co/UVEuUcviaF
4 362Views
30Likes
1Reposts
1Replies
0Quotes
1Bookmarks
Is that a lot?
0.47×vs this author's median9 348 views is typical
0Percentile for this authorof 5 recent posts
3.00×vs 10K–100K median1 456 views is typical
22.58%Reachviews ÷ followers
0.73%Engagement rateof viewers reacted