back to main landing Tweets ⌂

Tweet

2022-11-09T13:00:28+00:00 | 🔗

@rguha Wow, yes, very similar algorithm in structure. The learning rate for SPE is like the noise level for diffusion. There probably is an argument that diffusion models are relearning the update step/distance metric of the SPE, and perhaps learning those with better-calibrated values https://t.co/aSqxPRzySp

Tweet image for 1590328469019193345
← Previous Tweet Next Tweet →
ATLANTIC CNN FOX NYT POLITICO QUANTA SEMAFOR TECHNOLOGYREVIEW WSJ
ALL IN CONVERSATIONS W TYLER ECON102 EZRA KLEIN SHOW GRAY AREA HARD FORK HARDCORE HISTORY ODD LOTS ON W KARA SWISHER
ALIGNMENT FORUM BEN THOMPSON DAILY NOUS HACKERNEWS LESSWRONG MATT DRUDGE MATTHEW YGLESIAS NATE SILVER NOAH SMITH PLATFORMER
ANDREJ KARPATHY ANDREW WHITE DARIO AMODEI DILEEP GEORGE GWERN LILIAN WENG PAT WALTERS PAUL GRAHAM SAM ALTMAN STEPHEN WOLFRAM TERENCE TAO
Where else should I get information from? contact me somehow if I'm missing something, I really appreciate new interesting sources of information.