PHIL LONG
Updated 44 days ago
P. L. Bartlett, D. P. Helmbold and P. M. Long. Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks. Neural Computation, 31: 477-502, 2019...
P. Awasthi, M. F. Balcan and P. M. Long. The power of localization for efficiently learning linear separators with noise. JACM, 63(6): 50:1-50:27, 2017...
P. L. Bartlett, P. M. Long and O. Bousquet. The dynamics of Sharpness-Aware Minimization: bouncing across ravines and drifting towards wide minima. JMLR, 24(316):1-36, 2023.