Research Interests
  • Probability theory: limit theorems for Markov chains, large deviation theory, stochastic
    processes and stochastic ODEs
  • Dynamical systems and ergodic theory
  • Statistics with applications to data science
  • Machine Learning interpretability
  1. A. Miroshnikov, K. Kotsiopoulos, and A. Ravi Kannan, “Mutual information-based group explainers with coalition structure for machine learning model explanations”, (2021), arxiv:2102.10878.
  2. A. Miroshnikov, K. Kotsiopoulos, R. Franks and A. Ravi Kannan, “Wasserstein-based fairness interpretability framework for machine learning models”, (2020), arxiv:2011.03156.
  3. A. Miroshnikov, K. Kotsiopoulos and E. Conlon, “Asymptotic properties and approximation of Bayesian logspline density estimators for communication-free parallel computing methods“, Submitted (2018), arxiv:1710.09071.