4 papers · 1 filter
Informative Post-Hoc Explanations Only Exist for Simple Functions
Eric Günther, Balázs Szabados, Robi Bhattacharjee +2
Many researchers have suggested that local post-hoc explanation algorithms can be used to gain insights into the behavior of complex machine learning models. However, theoretical g…
How to safely discard features based on aggregate SHAP values
Robi Bhattacharjee, Karolin Frohnapfel, Ulrike von Luxburg
SHAP is one of the most popular local feature-attribution methods. Given a function f and an input x, it quantifies each feature's contribution to f(x). Recently, SHAP has been inc…
Auditing Local Explanations is Hard
Robi Bhattacharjee, Ulrike von Luxburg
In sensitive contexts, providers of machine learning algorithms are increasingly required to give explanations for their algorithms' decisions. However, explanation receivers might…
Beyond Discrepancy: A Closer Look at the Theory of Distribution Shift
Robi Bhattacharjee, Nick Rittler, Kamalika Chaudhuri
Many machine learning models appear to deploy effortlessly under distribution shift, and perform well on a target distribution that is considerably different from the training dist…