MXFusion: A Modular Deep Probabilistic Programming Library

By Zhenwen Dai, Eric Meissner, Neil D. Lawrence. 2018

12 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Tim Januschowski
2. Jan Gasthaus
3. Danijar Hafner
4. Syama Sundar Rangapuram
5. Konstantinos Benidis
6. David Salinas
7. Dustin Tran
8. Michael W. Dusenberry

Citations in the corpus

• Deep Factors for Forecasting (2019, methodology): “Our algorithms are implemented in MXNet Gluon (Chen et al., 2015), and make extensive use of its Linear Algebra library (Seeger et al., 2017; Zhenwen et al., 2018).”
• Bayesian Layers: A Module for Neural Network Uncertainty (2018, background): “A closely related concept is MXFusion’s probabilistic module (Dai et al., 2018), a module which implements a set of random variables alongside a dedicated inference algorithm.”
• GluonTS: Probabilistic Time Series Models in Python (2019, background): “In recent years, more application-specific toolkits have appeared primarily in those areas where deep learning has been overwhelmingly successful, such as computer vision and language-related tasks, but also increasingly beyond (Hieber et al., 2018; Dai et al., 2018; Bingham et al., 2018).”