Search Results for author:
Found 3 papers, 3 papers with code
Mixtures of All Trees
We show that it is possible to parameterize this Mixture of All Trees (MoAT) model compactly (using a polynomial-size representation) in a way that allows for tractable likelihood computation and optimization via stochastic gradient descent.
Certifying Fairness of Probabilistic Circuits
In this paper, we propose an algorithm to search for discrimination patterns in a general class of probabilistic models, namely probabilistic circuits.
The Tail Wagging the Dog: Dataset Construction Biases of Social Bias Benchmarks
How reliably can we trust the scores obtained from social bias benchmarks as faithful indicators of problematic social biases in a given language model?
Cannot find the paper you are looking for? You can
Submit a new open access paper.
