no code implementations • 17 Mar 2023 • Konstandinos Kotsiopoulos, Alexey Miroshnikov, Khashayar Filom, Arjun Ravi Kannan
In our work, we focus on a wide class of linear game values, as well as coalitional values, for the marginal game based on a given ML model and predictor vector.
1 code implementation • 16 Feb 2023 • Khashayar Filom, Alexey Miroshnikov, Konstandinos Kotsiopoulos, Arjun Ravi Kannan
We exploit the symmetry to derive an explicit formula, with improved complexity and only in terms of the internal model parameters, for marginal Shapley (and Banzhaf and Owen) values of CatBoost models.
no code implementations • 19 Nov 2021 • Alexey Miroshnikov, Konstandinos Kotsiopoulos, Ryan Franks, Arjun Ravi Kannan
The post-processing methodology involves reshaping the predictor distributions by balancing the positive and negative bias explanations and allows for the regressor bias to decrease.
no code implementations • 22 Feb 2021 • Alexey Miroshnikov, Konstandinos Kotsiopoulos, Arjun Ravi Kannan
The first part of our work formulates a stability theory for these explanation operators by establishing certain bounds for both marginal and conditional explanations.
Computer Science and Game Theory Probability 91A06, 91A12, 91A80, 46N30, 46N99, 68T01
no code implementations • 6 Nov 2020 • Alexey Miroshnikov, Konstandinos Kotsiopoulos, Ryan Franks, Arjun Ravi Kannan
The objective of this article is to introduce a fairness interpretability framework for measuring and explaining the bias in classification and regression models at the level of a distribution.