Explainable Artificial Intelligence (XAI) has garnered significant attention in recent years to
increase the transparency of AI models and systems and aid in decision-making. This is …

SHAP explanations are a popular feature-attribution mechanism for explainable AI. They
use game-theoretic notions to measure the influence of individual features on the prediction …

Feature importance estimates that inform users about the degree to which given inputs
influence the output of a predictive model are crucial for understanding, validating, and …

Probabilistic circuits (PCs) are a promising avenue for probabilistic modeling, as they permit
a wide range of exact and efficient inference routines. Recent “deep-learning-style” …

Data quality affects machine learning (ML) model performances, and data scientists spend
considerable amount of time on data cleaning before model training. However, to date, there …

Circuit representations are becoming the lingua franca to express and reason about
tractable generative and discriminative models. In this paper, we show how complex …

For a d-ary Boolean function Φ:{0, 1} d→{0, 1} and an assignment to its variables x=(x 1, x
2,..., xd) we consider the problem of finding those subsets of the variables that are sufficient …

Machine learning (ML) applications have been thriving recently, largely attributed to the
increasing availability of data. However, inconsistency and incomplete information are …

Computing expected predictions of discriminative models is a fundamental task in machine
learning that appears in many interesting applications such as fairness, handling missing …

We present GPkit, a Python toolkit for Geometric and Signomial Programming that prioritizes
explainability and incremental complexity. GPkit was designed through an ethnographic …