News for hackers. Stuff that matters.
Re:Every Model Learned by Gradient Descent Is Approximately ... by hobofan on Sunday December 06, 2020 @11:31AM (#25324503)
Is this a new finding? I'm not an expert on the deeper mathematical side of ML, but I remember a friend of mine already telling me about something that sounded exactly like this (ca. 2016-17).
Re:Every Model Learned by Gradient Descent Is Approximately ... by ironSkillet on Sunday December 06, 2020 @12:55PM (#25325180)
The fact that kernel machines can approximate other models isn't new. I think the novel idea is that they have explicitly constructed the "translation" between the arbitrary model to the kernel machine, and it's quite clean.