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
Preprints
[pdf_file] K. Kotsiopoulos, A. Miroshnikov, K. Filom and A. Ravi Kannan, "Approximation of group explainers with coalition structure using Monte Carlo sampling on the product space of coalitions and features", arXiv:2303.10216 (2023).
[pdf_file] A. Miroshnikov, K. Kotsiopoulos, R. Franks and A. Ravi Kannan, "Model-agnostic bias mitigation methods with regressor distribution control for Wasserstein-based fairness metrics", arXiv:2111.11259 (2021).
[pdf_file] A. Miroshnikov, K. Kotsiopoulos, K. Filom and A. Ravi Kannan, "Stability theory of game-theoretic group feature explanations for machine learning models", arXiv:2102.10878 (2021).
[pdf_file] K. Kotsiopoulos, A. Miroshnikov and E. Conlon, "Asymptotic properties and approximation of Bayesian logspline density estimators for communication-free parallel computing methods", arXiv:1710.09071 (2018).
Published/Accepted Papers
[link] K. Filom, A. Miroshnikov, K. Kotsiopoulos and A. Ravi Kannan, "On marginal feature attributions of tree-based models", Foundations of Data Science (2024), doi:10.3934/fods.2024021
[link] A. Miroshnikov, K. Kotsiopoulos, R. Franks and A. Ravi Kannan, "Wasserstein-based fairness interpretability framework for machine learning models", Machine Learning (2022), doi:10.1007/s10994-022-06213-9
Patent Applications
[pdf_file] US-20220414766-A1, "COMPUTING SYSTEM AND METHOD FOR CREATING A DATA SCIENCE MODEL HAVING REDUCED BIAS", (2022)
[pdf_file] US-20210383268-A1, "SYSTEM AND METHOD FOR MITIGATING BIAS IN CLASSIFICATION SCORES GENERATED BY MACHINE LEARNING MODELS", (2021)
[pdf_file] US-20210383275-A1, "SYSTEM AND METHOD FOR UTILIZING GROUPED PARTIAL DEPENDENCE PLOTS AND GAME-THEORETIC CONCEPTS AND THEIR EXTENSIONS IN THE GENERATION OF ADVERSE ACTION REASON CODES", (2021)
[pdf_file] US-20210350272-A1, "SYSTEM AND METHOD FOR UTILIZING GROUPED PARTIAL DEPENDENCE PLOTS AND SHAPLEY ADDITIVE EXPLANATIONS IN THE GENERATION OF ADVERSE ACTION REASON CODES", (2021)