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

9 papers

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…

cs.GT2020

Game on Random Environment, Mean-field Langevin System and Neural Networks

Giovanni Conforti, Anna Kazeykina, Zhenjie Ren

In this paper we study a type of games regularized by the relative entropy, where the players' strategies are coupled through a random environment variable. Besides the existence a…

math.OC20191 cited

Mean Field Games with Branching

Julien Claisse, Zhenjie Ren, Xiaolu Tan

Mean field games are concerned with the limit of large-population stochastic differential games where the agents interact through their empirical distribution. In the classical set…

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…