ArviZ a unified library for exploratory analysis of Bayesian models in Python

By Ravi Kumar, Colin Carroll, Ari Hartikainen, Osvaldo A. Martin. Journal of Open Source Software, 2019

561 citations recorded by the source corpus.

While conceptually simple, Bayesian methods can be mathematically and numerically challenging. Probabilistic programming languages (PPLs) implement functions to easily build Bayesian models together with efficient automatic inference methods. This helps separate the model building from the inference, allowing practitioners to focus on their specific problems and leaving PPLs to handle the computational details for them (Daniel Roy 2015; Bessiere et al. 2013; Ghahramani 2015). The inference process generates a posterior distribution — which has a central role in Bayesian statistics — together with other distributions like the posterior predictive distribution and the prior predictive distribution. The correct visualization, analysis, and interpretation of these distributions is key to properly answer the questions that motivate the inference process.

Subfields: Artificial Intelligence, Management Science and Operations Research, Signal Processing

View Paper: https://www.semanticscholar.org/paper/67d3c1e98f7292c8d0519b33d1ca272138552978

How researchers see this paper

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

In Artificial Intelligence

1. Aki Vehtari
2. Andrew Gelman
3. Paul-Christian Burkner
4. Yuling Yao
5. Jonah Gabry
6. Daniel P. Simpson
7. Charles C. Margossian
8. Bob Carpenter

In Management Science and Operations Research

1. Andrew Gelman
2. Paul-Christian Burkner
3. Aki Vehtari
4. Jonah Gabry
5. Charles C. Margossian
6. Daniel P. Simpson
7. Osvaldo A. Martin
8. Thomas V. Wiecki

In Signal Processing

1. Jonah Gabry
2. Andrew Gelman
3. Aki Vehtari
4. Daniel P. Simpson
5. Yuling Yao
6. Charles C. Margossian

Citations in the corpus

• Discovery of the Pure Polycyclic Aromatic Hydrocarbon Indene (c-C9H8) with GOTHAM Observations of TMC-1 (2021, methodology): “Following convergence of the sampling, the resulting posterior was analyzed using the arviz suite of routines (Kumar et al. 2019), and the expected emission from indene is simulated using the posterior mean parameters shown in Table 2.”
• A Future Percent-level Measurement of the Hubble Expansion at Redshift 0.8 with Advanced LIGO (2019, unknown): “Software: Numpy (van der Walt et al. 2011), Scipy (Jones et al. 2001), IPython (Pérez & Granger 2007), Matplotlib (Hunter 2007), scikit-learn (Pedregosa et al. 2012), astropy (Astropy Collaboration et al. 2013; Price-Whelan et al. 2018), PyStan (Carpenter et al. 2017; Stan Development Team 2018), Se”
• Bayesian Workflow (2020, methodology): “, 2020a) or ArviZ (Kumar et al., 2019).”
• Pareto Smoothed Importance Sampling (2015, methodology): “PSIS has been also implemented, for example, in the widely used Python packages ArviZ (Kumar et al., 2019) and Pyro (Bingham et al.”
• PyMC: a modern, and comprehensive probabilistic programming framework in Python (2023, methodology): “The architecture also depends on two other libraries, PyTensor (see section PyTensor) and ArviZ ( Kumar et al., 2019 ), for computational backend functionality and exploratory analysis of Bayesian models, respectively.”