A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Improved KernelSHAP via linear regression for ML model interpretation.
A new method reduces the computational cost of KernelSHAP for explaining predictions.
Study shows safely discarding features based on aggregate SHAP values is sound.
New sampling methods improve Shapley values for explaining machine learning predictions.
Deep learning has demonstrated success in many applications; however, their use in healthcare has been limited due to the lack of transparency into how they generate predictions. Algorithms such as Recurrent Neural Networks (RNNs) when applied to Electronic Medical Records (EMR) introduce additional barriers to transpa…
PatternLocal improves XAI for non-linear models by suppressing suppressor variables.
ProxySHAP approximates Shapley and Banzhaf interactions efficiently.
This paper proposes an efficient method for calculating Shapley values in Naive Bayes classifiers.
mSHAP explains predictions of two-part models, improving fairness and interpretability.
Bayesian framework improves reliability and consistency of model explanations.