Jascha Sohl-Dickstein (@jaschasd) 's Twitter Profile
Jascha Sohl-Dickstein

@jaschasd

Member of the technical staff @ Anthropic. Most (in)famous for inventing diffusion models. AI + physics + neuroscience + dynamics.

ID: 65876824

linkhttps://sohldickstein.com calendar_today15-08-2009 11:00:03

544 Tweet

21,21K Takipçi

675 Takip Edilen

Jascha Sohl-Dickstein (@jaschasd) 's Twitter Profile Photo

Have you ever done a dense grid search over neural network hyperparameters? Like a *really dense* grid search? It looks like this (!!). Blueish colors correspond to hyperparameters for which training converges, redish colors to hyperparameters for which training diverges.