activity
20152022
most citedMean-field Langevin System, Optimal Control and Deep Neural Networks

11 citations · 18 across the 5 of their papers we have counts for

collaborators
Showing math.PRShow all

6 papers · 1 filter

math.PR2022

On path-dependent multidimensional forward-backward SDEs

Kaitong Hu, Zhenjie Ren, Nizar Touzi

This paper extends the results of Ma, Wu, Zhang, Zhang [11] to the context of path-dependent multidimensional forward-backward stochastic differential equations (FBSDE). By path-de…

math.PR20193 cited

Continuous-Time Principal-Agent Problem in Degenerate Systems

Kaitong Hu, Zhenjie Ren, Nizar Touzi

In this paper we present a variational calculus approach to Principal-Agent problem with a lump-sum payment on finite horizon in degenerate stochastic systems, such as filtered par…

math.PR201911 cited

Mean-field Langevin System, Optimal Control and Deep Neural Networks

Kaitong Hu, Anna Kazeykina, Zhenjie Ren

In this paper, we study a regularised relaxed optimal control problem and, in particular, we are concerned with the case where the control variable is of large dimension. We introd…

math.PR2019

Mean-Field Langevin Dynamics and Energy Landscape of Neural Networks

Kaitong Hu, Zhenjie Ren, David Siska +1

Our work is motivated by a desire to study the theoretical underpinning for the convergence of stochastic gradient type algorithms widely used for non-convex learning tasks such as…

math.PR2018

Viscosity solutions of path-dependent PDEs with randomized time

Zhenjie Ren, Mauro Rosestolato

We introduce a new definition of viscosity solution to path-dependent partial differential equations, which is a slight modification of the definition introduced in [8]. With the n…

math.PR20153 cited

Perron's method for viscosity solutions of semilinear path dependent PDEs

Zhenjie Ren

This paper proves the existence of viscosity solutions of path dependent semilinear PDEs via Perron's method, i.e. via showing that the supremum of viscosity subsolutions is a visc…