Michael Betancourt: Scalable Bayesian Inference with Hamiltonian Monte Carlo
Recording of Michael Betancourt's talk at the London Machine Learning Meetup: https://www.meetup.com/London-Machine-Learning-Meetup/events/251198486/
Despite the promise of big data, inferences are often limited not by sample size but rather by systematic effects. Only by carefully modeling these effects can we take full advantage of the data -- big data must be complemented with big models and the algorithms that can fit them. One such algorithm is Hamiltonian Monte Carlo, which exploits the inherent geometry of the posterior distribution to admit full Bayesian inference that scales to the complex models of practical interest. In this talk, I will discuss the conceptual foundations of Hamiltonian Monte Carlo, elucidating the geometric nature of its scalable performance and stressing the properties critical to a robust implementation.
Bio: Michael Betancourt is the principle research scientist with Symplectomorphic, LLC where he develops theoretical and methodological tools to support practical Bayesian inference. He is also a core developer of Stan, where he implements and tests these tools. In addition to hosting tutorials and workshops on Bayesian inference with Stan, he also collaborates on analyses in epidemiology, pharmacology, and physics, amongst others. Before moving into statistics, Michael earned a B.S. from the California Institute of Technology and a Ph.D. from the Massachusetts Institute of Technology, both in physics.
https://evolution.ai/ : Machines that Read - Intelligent data extraction from corporate and financial documents.
Видео Michael Betancourt: Scalable Bayesian Inference with Hamiltonian Monte Carlo канала London Machine Learning Meetup
Despite the promise of big data, inferences are often limited not by sample size but rather by systematic effects. Only by carefully modeling these effects can we take full advantage of the data -- big data must be complemented with big models and the algorithms that can fit them. One such algorithm is Hamiltonian Monte Carlo, which exploits the inherent geometry of the posterior distribution to admit full Bayesian inference that scales to the complex models of practical interest. In this talk, I will discuss the conceptual foundations of Hamiltonian Monte Carlo, elucidating the geometric nature of its scalable performance and stressing the properties critical to a robust implementation.
Bio: Michael Betancourt is the principle research scientist with Symplectomorphic, LLC where he develops theoretical and methodological tools to support practical Bayesian inference. He is also a core developer of Stan, where he implements and tests these tools. In addition to hosting tutorials and workshops on Bayesian inference with Stan, he also collaborates on analyses in epidemiology, pharmacology, and physics, amongst others. Before moving into statistics, Michael earned a B.S. from the California Institute of Technology and a Ph.D. from the Massachusetts Institute of Technology, both in physics.
https://evolution.ai/ : Machines that Read - Intelligent data extraction from corporate and financial documents.
Видео Michael Betancourt: Scalable Bayesian Inference with Hamiltonian Monte Carlo канала London Machine Learning Meetup
Показать
Комментарии отсутствуют
Информация о видео
15 июля 2018 г. 19:39:34
00:53:20
Другие видео канала
The intuition behind the Hamiltonian Monte Carlo algorithm#6 A principled Bayesian workflow, with Michael BetancourtPaul Bürkner: An introduction to Bayesian multilevel modeling with brmsHamiltonian Monte Carlo For Dummies (Statisticians / Pharmacometricians / All)Warren Powell, "Stochastic Optimization Challenges in Energy"Bayesian Online Change-Point Detection - Schroders [Tech Sessions]First Steps in Symplectic Dynamics - Helmut HoferWhy I don't work for FAANGBrenden Lake | Compositional generalization in minds and machinesL4.4 Dirac equation for the electron and hydrogen HamiltonianData Science Sydney Michael BetancourtPhysics - Adv. Mechanics: Hamiltonian Mech. (1 of 18) What is Hamiltonian Mechanics?Scalable Bayesian Inference with Hamiltonian Monte CarloSome Bayesian Modeling Techniques in StanEfficient Bayesian inference with Hamiltonian Monte Carlo -- Michael Betancourt (Part 1)Tech talk: A practical introduction to Bayesian hierarchical modellingHamiltonian Monte CarloWelcome to the official Stan youtube channel!A conceptual introduction to Hamiltonian Monte Carlo"Probabilistic Programming and Bayesian Inference in Python" - Lara Kattan (Pyohio 2019)