Collaborating Authors


Bean Machine: Composable, Fast Probabilistic Inference on PyTorch


Today, we're excited to announce an early beta release of Bean Machine, a PyTorch-based probabilistic programming system that makes it easy to represent and to learn about uncertainties in the machine learning models that we work with every day. Bean Machine enables you to develop domain-specific probabilistic models, and automatically learn about unobserved properties of the model with automatic, uncertainty-aware learning algorithms. Though powerful, probabilistic modeling does take some getting used to. If this is your first exposure to the topic, we welcome you to check out a short overview of the concept in the Fabulous Adventures in Coding blog. We on the Bean Machine development team believe that the usability of a system forms the bedrock for its success, and we've taken care to center Bean Machine's design around a declarative philosophy within the PyTorch ecosystem.