Research

My research interests include mathematical finance, stochastic analysis, game theory and machine learning.

  • Zhengqi Wu and Renyuan Xu. Risk-sensitive Reinforcement Learning under General Utility Functions , Preprint, 2023.
  • Ben Hambly, Renyuan Xu and Huining Yang. Partially Observable Linear-quadratic Games with Information Corrections , Preprint, 2023.
  • Renyuan Xu, Thaleia Zariphopoulou and Luhao Zhang. Reversible and Irreversible Decisions under Costly Information Acquisition , Preprint, 2023.
  • Rama Cont, Alain Rossier and Renyuan Xu. Asymptotic Analysis of Deep Residual Networks , Submitted, 2023.
  • Yinbin Han, Meisam Razaviyayn and Renyuan Xu. Policy Gradient Finds Global Optimum of Nearly Linear-quadratic Control Systems, Submitted, 2023.
    • Short version accepted by NeurIPS 2022 Workshop on Optimization for Machine Learning.
  • Jingwei Ji, Renyuan Xu and Ruihao Zhu. Risk-Aware Linear Bandits: Theory and Applications in Smart Order Routing, Submitted, 2023.
    • Short version accepted by the 3rd ACM International Conference of AI in Finance (ICAIF'22).
    • Short version accepted for full presentation at INFORMS 6TH Workshop on Data Science.
  • Rama Cont, Alain Rossier and Renyuan Xu. Convergence and Implicit Regularization Properties of Gradient Descent for Deep Residual Networks, Rreprint, 2022.
  • Rama Cont, Mihai Cucuringu, Renyuan Xu and Chao Zhang. TailGAN: Nonparametric Scenario Genration for Tail Risk Estimation, Submitted, 2022.
  • Haotian Gu, Xin Guo, Xiaoli Wei and Renyuan Xu. Mean-Field Multi-Agent Reinforcement Learning: A Decentralized Network Approach, Revision, Mathematics of Operations Research, 2022.
  • Ben Hambly, Renyuan Xu and Huining Yang. Recent Advances in Reinforcement Learning in Finance, To appear, Mathematical Finance, 2023.
  • Ben Hambly, Renyuan Xu and Huining Yang. Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games, To appear, Journal of Machine Learning Research (JMLR), 2023.
  • Alain-Sam Cohen, Rama Cont, Alain Rossier and Renyuan Xu. Scaling Properties of Deep Residual Networks, International Conference on Machine Learning (ICML), 2021.
  • Anna Ananova, Rama Cont, and Renyuan Xu. Excursion Risk, Preprint, 2020.
  • Rama Cont, Artur Kotlicki and Renyuan Xu. Modelling COVID-19 Contagion: Risk Assessment and Targeted Mitigation Policies, Royal Society Open Science, 2021.
  • Rama Cont, Xin Guo and Renyuan Xu. Interbank Lending with Benchmark Rate: Pareto Optima for a Class of Singular Control Games, Mathematical Finance, 2021.
  • Ben Hambly, Renyuan Xu and Huining Yang. The Policy Gradient method for the Noisy Linear Quadratic Regulator over a Finite Horizon, SIAM Journal on Control and Optimization, 2021.
  • Xin Guo, Renyuan Xu and Thaleia Zariphopoulou. Entropy Regularization for Mean Field Games with Learning, Mathematics of Operations Research, 2021.
  • Haotian Gu, Xin Guo, Xiaoli Wei and Renyuan Xu. Mean-Field Controls with Q-learning for Cooperative MARL: Convergence and Complexity Analysis , SIAM Journal on Mathematics of Data Science (SIMODS), 2021.
    • Short version, ICML 2020 Workshop on Theory of Reinforcement Learning.
  • Haotian Gu, Xin Guo, Xiaoli Wei and Renyuan Xu. Dynamic Programming Principles for Learning Mean-Field Controls, Operations Research, 2022.
  • Xin Guo, Anran Hu, Renyuan Xu and Junzi Zhang. General Framework for Learning Mean-Field Games, Accepted, Mathematics of Operations Research, 2021.
  • Zhengyuan Zhou, Renyuan Xu and Jose Blanchet. Delay-Adaptive Learning in Generalized Linear Contextual Bandits, Accepted, Mathematics of Operations Research, 2021.
  • Xin Guo, Wenpin Tang, and Renyuan Xu. A Class of Stochastic Games and Stochastic Free Boundary Problems, Accepted, SIAM Journal on Control and Optimization, 2021.
  • Xin Guo, Charles-Albert Lehalle, and Renyuan Xu. Transaction Cost Data Analytics for Corporate Bonds, Accepted, Quantitative Finance, 2020.
  • Xin Guo and Renyuan Xu. Stochastic Games for Fuel Followers Problem: N vs MFG, SIAM Journal of Control and Optimization, 2019.
  • Xin Guo, Anran Hu, Renyuan Xu and Junzi Zhang. Consistency and Computation of Regularized MLEs for Multivariate Hawkes Processes, Submitted, 2018.
    • Short version, NeurIPS 2018 Workshop on Causality.
  • Robert Almgren and Renyuan Xu. Smart Order Routing via Statistical Learning, Preprint, 2019.