← Search

Steven Braun

2 accepted papers

2023

Probabilistic circuits that know what they don’t know

UAI 2023poster

Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data. In this paper, we show that PCs are in fact not robust to OOD data, i.e., they do…