Search Results for author:
Found 6 papers, 0 papers with code
Tightening Bounds on Probabilities of Causation By Merging Datasets
Existing work to further tighten these bounds by leveraging extra information either provides numerical bounds, symbolic bounds for fixed dimensionality, or requires access to multiple datasets that contain the same treatment and outcome variables.
Bounding probabilities of causation through the causal marginal problem
In the absence of such assumptions, existing work requires multiple observations of datasets that contain the same treatment and outcome variables, in order to establish bounds on these probabilities.
A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?
We find this area of research has received disproportionately less attention relative to adversarial machine learning, yet a significant robustness gap exists that manifests in performance degradation similar in magnitude to adversarial conditions.
Multiply Robust Causal Mediation Analysis with Continuous Treatments
For binary treatments, efficient estimators for the direct and indirect effects are presented in Tchetgen Tchetgen and Shpitser (2012) based on the influence function of the parameter of interest.
A Semiparametric Approach to Interpretable Machine Learning
In order to combat this shortcoming, we propose a novel approach to trading off interpretability and performance in prediction models using ideas from semiparametric statistics, allowing us to combine the interpretability of parametric regression models with performance of nonparametric methods.
Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning
However, existing approaches have two important shortcomings: (i) the "explanatory units" are micro-level inputs into the relevant prediction model, e. g., image pixels, rather than interpretable macro-level features that are more useful for understanding how to possibly change the algorithm's behavior, and (ii) existing approaches assume there exists no unmeasured confounding between features and target model predictions, which fails to hold when the explanatory units are macro-level variables.
