## Dynamics of Deep Neural Networks--A Fourier Analysis Perspective

Yaoyu Zhang

Member, School of Mathematics

October 4, 2019

Yaoyu Zhang

Member, School of Mathematics

October 4, 2019

Zhengyi Zhou

Member, School of Mathematics

October 4, 2019

Vladimir Drinfeld

The University of Chicago; Visiting Professor, School of Mathematics

October 3, 2019

The stacky approach was originated by Bhatt and Lurie. (But the possible mistakes in my talk are mine.)

Let X be a scheme over F_p. Many years ago Grothendieck and Berthelot defined the notion of crystal on X; moreover, they defined the notion of crystalline cohomology of a crystal.

Jan Vonk

Member, School of Mathematics

October 2, 2019

Elad Hazan

Princeton University, Google AI Princeton

October 2, 2019

Linear dynamical systems are a continuous subclass of reinforcement learning models that are widely used in robotics, finance, engineering, and meteorology. Classical control, since the works of Kalman, has focused on dynamics with Gaussian i.i.d. noise, quadratic loss functions and, in terms of provably efficient algorithms, known systems and observed state.

Zhao Song

Member, School of Mathematics

October 2, 2019

Raphael Steiner

Member, School of Mathematics

October 2, 2019

Jason Lee

Member, School of Mathematics

October 2, 2019

Sahil Singla

Member, School of Mathematics

October 2, 2019

Remy van Dobben de Bruyn

Veblen Research Instructor, School of Mathematics

October 2, 2019