Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations
Bayesian probabilistic modeling is supported by powerful computational tools like probabilistic programming and efficient Markov Chain Monte Carlo (MCMC) sampling. However, the results of Bayesian inference are challenging for users to interpret in tasks like decision-making under uncertainty or mod...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-12-01
|
| Series: | Frontiers in Computer Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcomp.2020.567344/full |
| _version_ | 1823940176458547200 |
|---|---|
| author | Evdoxia Taka Sebastian Stein John H. Williamson |
| author_facet | Evdoxia Taka Sebastian Stein John H. Williamson |
| author_sort | Evdoxia Taka |
| collection | DOAJ |
| description | Bayesian probabilistic modeling is supported by powerful computational tools like probabilistic programming and efficient Markov Chain Monte Carlo (MCMC) sampling. However, the results of Bayesian inference are challenging for users to interpret in tasks like decision-making under uncertainty or model refinement. Decision-makers need simultaneous insight into both the model's structure and its predictions, including uncertainty in inferred parameters. This enables better assessment of the risk overall possible outcomes compatible with observations and thus more informed decisions. To support this, we see a need for visualization tools that make probabilistic programs interpretable to reveal the interdependencies in probabilistic models and their inherent uncertainty. We propose the automatic transformation of Bayesian probabilistic models, expressed in a probabilistic programming language, into an interactive graphical representation of the model's structure at varying levels of granularity, with seamless integration of uncertainty visualization. This interactive graphical representation supports the exploration of the prior and posterior distribution of MCMC samples. The interpretability of Bayesian probabilistic programming models is enhanced through the interactive graphical representations, which provide human users with more informative, transparent, and explainable probabilistic models. We present a concrete implementation that translates probabilistic programs to interactive graphical representations and show illustrative examples for a variety of Bayesian probabilistic models. |
| first_indexed | 2024-12-17T04:09:57Z |
| format | Article |
| id | doaj.art-159a6dfc8d4c49f7a26a589dfc3c1357 |
| institution | Directory Open Access Journal |
| issn | 2624-9898 |
| language | English |
| last_indexed | 2024-12-17T04:09:57Z |
| publishDate | 2020-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Computer Science |
| spelling | doaj.art-159a6dfc8d4c49f7a26a589dfc3c13572022-12-21T22:04:15ZengFrontiers Media S.A.Frontiers in Computer Science2624-98982020-12-01210.3389/fcomp.2020.567344567344Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive RepresentationsEvdoxia TakaSebastian SteinJohn H. WilliamsonBayesian probabilistic modeling is supported by powerful computational tools like probabilistic programming and efficient Markov Chain Monte Carlo (MCMC) sampling. However, the results of Bayesian inference are challenging for users to interpret in tasks like decision-making under uncertainty or model refinement. Decision-makers need simultaneous insight into both the model's structure and its predictions, including uncertainty in inferred parameters. This enables better assessment of the risk overall possible outcomes compatible with observations and thus more informed decisions. To support this, we see a need for visualization tools that make probabilistic programs interpretable to reveal the interdependencies in probabilistic models and their inherent uncertainty. We propose the automatic transformation of Bayesian probabilistic models, expressed in a probabilistic programming language, into an interactive graphical representation of the model's structure at varying levels of granularity, with seamless integration of uncertainty visualization. This interactive graphical representation supports the exploration of the prior and posterior distribution of MCMC samples. The interpretability of Bayesian probabilistic programming models is enhanced through the interactive graphical representations, which provide human users with more informative, transparent, and explainable probabilistic models. We present a concrete implementation that translates probabilistic programs to interactive graphical representations and show illustrative examples for a variety of Bayesian probabilistic models.https://www.frontiersin.org/articles/10.3389/fcomp.2020.567344/fullBayesian probabilistic modelingBayesian inferenceprobabilistic programmingMarkov Chain Monte Carlo (MCMC)uncertainty visualizationinteractive visualization |
| spellingShingle | Evdoxia Taka Sebastian Stein John H. Williamson Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations Frontiers in Computer Science Bayesian probabilistic modeling Bayesian inference probabilistic programming Markov Chain Monte Carlo (MCMC) uncertainty visualization interactive visualization |
| title | Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations |
| title_full | Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations |
| title_fullStr | Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations |
| title_full_unstemmed | Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations |
| title_short | Increasing Interpretability of Bayesian Probabilistic Programming Models Through Interactive Representations |
| title_sort | increasing interpretability of bayesian probabilistic programming models through interactive representations |
| topic | Bayesian probabilistic modeling Bayesian inference probabilistic programming Markov Chain Monte Carlo (MCMC) uncertainty visualization interactive visualization |
| url | https://www.frontiersin.org/articles/10.3389/fcomp.2020.567344/full |
| work_keys_str_mv | AT evdoxiataka increasinginterpretabilityofbayesianprobabilisticprogrammingmodelsthroughinteractiverepresentations AT sebastianstein increasinginterpretabilityofbayesianprobabilisticprogrammingmodelsthroughinteractiverepresentations AT johnhwilliamson increasinginterpretabilityofbayesianprobabilisticprogrammingmodelsthroughinteractiverepresentations |