Zobrazeno 1 - 10
of 30
pro vyhledávání: '"Corenflos, Adrien"'
Given an unconditional diffusion model $\pi(x, y)$, using it to perform conditional simulation $\pi(x \mid y)$ is still largely an open question and is typically achieved by learning conditional drifts to the denoising SDE after the fact. In this wor
Externí odkaz:
http://arxiv.org/abs/2405.13794
Autor:
Cabezas, Alberto, Corenflos, Adrien, Lao, Junpeng, Louf, Rémi, Carnec, Antoine, Chaudhari, Kaustubh, Cohn-Gordon, Reuben, Coullon, Jeremie, Deng, Wei, Duffield, Sam, Durán-Martín, Gerardo, Elantkowski, Marcin, Foreman-Mackey, Dan, Gregori, Michele, Iguaran, Carlos, Kumar, Ravin, Lysy, Martin, Murphy, Kevin, Orduz, Juan Camilo, Patel, Karm, Wang, Xi, Zinkov, Rob
BlackJAX is a library implementing sampling and variational inference algorithms commonly used in Bayesian computation. It is designed for ease of use, speed, and modularity by taking a functional approach to the algorithms' implementation. BlackJAX
Externí odkaz:
http://arxiv.org/abs/2402.10797
In this paper, we propose a novel approach to Bayesian experimental design for non-exchangeable data that formulates it as risk-sensitive policy optimization. We develop the Inside-Out SMC$^2$ algorithm, a nested sequential Monte Carlo technique to i
Externí odkaz:
http://arxiv.org/abs/2402.07868
Autor:
Corenflos, Adrien, Finke, Axel
State-of-the-art methods for Bayesian inference in state-space models are (a) conditional sequential Monte Carlo (CSMC) algorithms; (b) sophisticated 'classical' MCMC algorithms like MALA, or mGRAD from Titsias and Papaspiliopoulos (2018, arXiv:1610.
Externí odkaz:
http://arxiv.org/abs/2401.14868
Stochastic optimal control of dynamical systems is a crucial challenge in sequential decision-making. Recently, control-as-inference approaches have had considerable success, providing a viable risk-sensitive framework to address the exploration-expl
Externí odkaz:
http://arxiv.org/abs/2312.14000
Probabilistic ordinary differential equation (ODE) solvers have been introduced over the past decade as uncertainty-aware numerical integrators. They typically proceed by assuming a functional prior to the ODE solution, which is then queried on a gri
Externí odkaz:
http://arxiv.org/abs/2401.03338
Autor:
Bosch, Nathanael, Corenflos, Adrien, Yaghoobi, Fatemeh, Tronarp, Filip, Hennig, Philipp, Särkkä, Simo
Probabilistic numerical solvers for ordinary differential equations (ODEs) treat the numerical simulation of dynamical systems as problems of Bayesian state estimation. Aside from producing posterior distributions over ODE solutions and thereby quant
Externí odkaz:
http://arxiv.org/abs/2310.01145
Monte Carlo methods - such as Markov chain Monte Carlo (MCMC) and piecewise deterministic Markov process (PDMP) samplers - provide asymptotically exact estimators of expectations under a target distribution. There is growing interest in alternatives
Externí odkaz:
http://arxiv.org/abs/2306.15422
Autor:
Corenflos, Adrien, Abdulsamad, Hany
We present a novel approach to approximate Gaussian and mixture-of-Gaussians filtering. Our method relies on a variational approximation via a gradient-flow representation. The gradient flow is derived from a Kullback--Leibler discrepancy minimizatio
Externí odkaz:
http://arxiv.org/abs/2303.06398
Autor:
Corenflos, Adrien, Särkkä, Simo
We introduce two new classes of exact Markov chain Monte Carlo (MCMC) samplers for inference in latent dynamical models. The first one, which we coin auxiliary Kalman samplers, relies on finding a linear Gaussian state-space model approximation aroun
Externí odkaz:
http://arxiv.org/abs/2303.00301