//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Under He/Lecun inits, theory implies Kernel OR Unstable regimes as width→∞. Discrepancies (e.g. feature learning) are seen as finite width effects. Our #NeurIPS2025 spotlight refutes this: practical nets do not converge to kernel limits; Feature learning persists as width→∞🧵