Filters








4 Hits in 2.4 sec

Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale [article]

Atılım Güneş Baydin, Lei Shao, Wahid Bhimji, Lukas Heinrich, Lawrence Meadows, Jialin Liu, Andreas Munk, Saeid Naderiparizi, Bradley Gram-Hansen, Gilles Louppe, Mingfei Ma, Xiaohui Zhao, Philip Torr, Victor Lee (+3 others)
2019 arXiv   pre-print
To address these, we present a novel PPL framework that couples directly to existing scientific simulators through a cross-platform probabilistic execution protocol and provides Markov chain Monte Carlo  ...  Probabilistic programming languages (PPLs) are receiving widespread attention for performing Bayesian inference in complex generative models.  ...  ACKNOWLEDGMENTS The authors would like to acknowledge valuable discussions with Thorsten  ... 
arXiv:1907.03382v2 fatcat:v4yy3ywsqrcr3fblgbkohvn264

Simulation-Based Inference for Global Health Decisions [article]

Christian Schroeder de Witt, Bradley Gram-Hansen, Nantas Nardelli, Andrew Gambardella, Rob Zinkov, Puneet Dokania, N. Siddharth, Ana Belen Espinosa-Gonzalez, Ara Darzi, Philip Torr, Atılım Güneş Baydin
2020 arXiv   pre-print
(https://github.com/SwissTPH/openmalaria) into probabilistic programs, enabling efficient interpretable Bayesian inference within those simulators.  ...  Here we discuss recent breakthroughs in machine learning, specifically in simulation-based inference, and explore its potential as a novel venue for model calibration to support the design and evaluation  ...  Etalumis: Bringing Probabilistic Programming to Scientific Simulators at Scale.  ... 
arXiv:2005.07062v1 fatcat:mrfht42puvb4tc2uq35itltjjm

Detecting and Quantifying Malicious Activity with Simulation-based Inference [article]

Andrew Gambardella, Bogdan State, Naeemullah Khan, Leo Tsourides, Philip H. S. Torr, Atılım Güneş Baydin
2021 arXiv   pre-print
We propose the use of probabilistic programming techniques to tackle the malicious user identification problem in a recommendation algorithm.  ...  Probabilistic programming provides numerous advantages over other techniques, including but not limited to providing a disentangled representation of how malicious users acted under a structured model,  ...  Etalumis: Bringing probabilistic programming to scientific simulators at scale. In C., and Baydin, A. G. Spacecraft Collision Risk Assess- ment with Probabilistic Programming.  ... 
arXiv:2110.02483v2 fatcat:xflyfy6slvfzbhizsb23ymgmnm

Simulation-based inference methods for particle physics [article]

Johann Brehmer, Kyle Cranmer
2020 arXiv   pre-print
Finally, we discuss probabilistic programming, an emerging paradigm that lets us extend inference to the latent process of the simulator.  ...  They allow us to generate high-fidelity simulated data, but they are not well-suited for inference on the theory parameters with observed data.  ...  Acknowledgments We want to thank our collaborators Zubair Bhatti, Sally Dawson, Irina Espejo, Joeri Hermans, Samuel Homiller, Felix Kling, Gilles Louppe, Siddharth Mishra-Sharma, Juan Pavez, Sinclert Perez  ... 
arXiv:2010.06439v2 fatcat:vc2wfdaq5razvjcz42xt7pim5m