Two papers have been accepted for ICLR2021

The following two papers have been accepted for International Conference on Learning Representations (ICLR2021).

Atsushi Nitanda and Taiji Suzuki: "Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime"

Shun-ichi Amari, Jimmy Ba, Roger Grosse, Xuechen Li, Atsushi Nitanda, Taiji Suzuki, Denny Wu, and Ji Xu: "When Does Preconditioning Help or Hurt Generalization?"