Publications

($\alpha-\beta$: alphabetical authorship)

Journal Papers

• Strongly Efficient Rare-Event Simulation for Regularly Varying Lévy Processes with Infinite Activities [preprint]
  Xingyu Wang, Chang-Han Rhee
  To appear at Mathematics of Operations Research

Submitted and Working Papers

• Large Deviations and Metastability Analysis for Heavy-Tailed Dynamical Systems [preprint]
  Xingyu Wang, Chang-Han Rhee
  Major Revision at Annals of Applied Probability
  Second Place, INFORMS George Nicholson Student Paper Competition, 2023
• Tail Asymptotics of Cluster Sizes in Multivariate Heavy-Tailed Hawkes Processes [preprint]
  ($\alpha-\beta$) Jose Blanchet, Roger J. A. Laeven, Xingyu Wang, Bert Zwart
  Major Revision at Annals of Applied Probability
• Sample Path Large Deviations for Multivariate Heavy-Tailed Hawkes Processes and Related Lévy Processes [preprint]
  ($\alpha-\beta$) Jose Blanchet, Roger J. A. Laeven, Xingyu Wang, Bert Zwart
  Major Revision at Bernoulli
• Global Dynamics of Heavy-Tailed SGDs in Nonconvex Loss Landscape: Characterization and Control [preprint]
  Xingyu Wang, Chang-Han Rhee
  Submitted to Operations Research

Conference Papers

• Multi-agent Multi-armed Bandit with Fully Heavy-tailed Dynamics [preprint]
  Xingyu Wang, Mengfan Xu
  Winter Simulation Conference, 2025
  
• Importance Sampling Strategy for Heavy-Tailed Systems with Catastrophe Principle
  Xingyu Wang, Chang-Han Rhee
  Winter Simulation Conference, 2023 [pdf]
• Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noises
  Xingyu Wang, Sewoong Oh, Chang-Han Rhee
  International Conference on Learning Representations (ICLR), 2022 [pdf]
  Nemhauser Prize for Best Student Paper, 2020
• Keyword-Based Topic Modeling and Keyword Selection
  Xingyu Wang, Lida Zhang, Diego Klabjan
  IEEE Big Data, 2021 [pdf]
• Rare-Event Simulation for Multiple Jump Events in Regularly Varying Lévy Processes with Infinite Activities
  Xingyu Wang, Chang-Han Rhee
  Winter Simulation Conference, 2020 [pdf]
• Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
  Xingyu Wang, Diego Klabjan
  International Conference on Machine Learning (ICML), 2018 [pdf]