11 citations · 15 across the 21 of their papers we have counts for
Showing 2022Show all
2 papers · 1 filter
stat.ML2022★ 11 cited
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
Jimmy Ba, Murat A. Erdogdu, Taiji Suzuki +3
We study the first gradient descent step on the first-layer parameters in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\topσ(\…
stat.ML2022★ 1 cited
Convex Analysis of the Mean Field Langevin Dynamics
Atsushi Nitanda, Denny Wu, Taiji Suzuki
As an example of the nonlinear Fokker-Planck equation, the mean field Langevin dynamics recently attracts attention due to its connection to (noisy) gradient descent on infinitely…