Search papers, labs, and topics across Lattice.
2
0
2
1
Forget philosophical debates: a practical "learning mechanics" is crystallizing to explain *how* deep learning works, not just *why* it should.
Edge of Stability isn't just a Euclidean thing: a generalized sharpness measure reveals that non-Euclidean gradient descent also operates at the edge, offering a single spectral measure across diverse optimizers.
