A Solvable High-Dimensional Model of GAN | Chuang Wang · Hong Hu · Yue Lu |
Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis | Yuki Yoshida · Masato Okada |
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup | Sebastian Goldt · Madhu Advani · Andrew Saxe · Florent Krzakala · Lenka Zdeborová |
First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise | Thanh Huy Nguyen · Umut Simsekli · Mert Gurbuzbalaban · Gaël RICHARD |
The Normalization Method for Alleviating Pathological Sharpness in Wide Neural Networks | Ryo Karakida · Shotaro Akaho · Shun-ichi Amari |
Untangling in Invariant Speech Recognition | Cory Stephenson · Jenelle Feather · Suchismita Padhy · Oguz Elibol · Hanlin Tang · Josh McDermott · SueYeon Chung |
Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes | Greg Yang |