FSML
FSML
Home
People
News
Publications
Contact
Light
Dark
Automatic
Paper-Conference
Scalable Data Assimilation with Message Passing
Data assimilation is a core component of numerical weather prediction systems. The large quantity of data processed during assimilation …
Oscar Key
,
So Takao
,
Daniel Giles
,
Marc Peter Deisenroth
Cite
Code
arXiv
A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods
We establish the first mathematically rigorous link between Bayesian, variational Bayesian, and ensemble methods. A key step towards …
Veit Wild
,
Sahra Ghalebikesabi
,
Dino Sejdinovic
,
Jeremias Knoblauch
Cite
arXiv
Meta-learning Control Variates: Variance Reduction with Limited Data
Control variates can be a powerful tool to reduce the variance of Monte Carlo estimators, but constructing effective control variates …
Zhuo Sun
,
Chris J Oates
,
François-Xavier Briol
PDF
Cite
Code
Multilevel Bayesian Quadrature
Multilevel Monte Carlo is a key tool for approximating integrals involving expensive scientific models. The idea is to use …
Kaiyu Li
,
Daniel Giles
,
Toni Karvonen
,
Serge Guillas
,
François-Xavier Briol
PDF
Cite
Code
No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models
The computation necessary for training Transformer-based language models has skyrocketed in recent years. This trend has motivated …
Jean Kaddour
,
Oscar Key
,
Piotr Nawrot
,
Pasquale Minervini
,
Matt J. Kusner
Cite
Code
arXiv
Robustifying likelihoods by optimistically re-weighting data
Likelihood-based inferences have been remarkably successful in wide-spanning application areas. However, even after due diligence in …
Miheer Dewaskar
,
Chris Tosh
,
Jeremias Knoblauch
,
David Dunson
Cite
arXiv
Vector-Valued Control Variates
Control variates are variance reduction tools for Monte Carlo estimators. They can provide significant variance reduction, but usually …
Zhuo Sun
,
Alessandro Barp
,
François-Xavier Briol
PDF
Cite
Code
Bayesian Numerical Integration with Neural Networks
Bayesian probabilistic numerical methods for numerical integration offer significant advantages over their non-Bayesian counterparts: …
Katharina Ott
,
Michael Tiemann
,
Philipp Hennig
,
François-Xavier Briol
Cite
arXiv
Optimally-Weighted Estimators of the Maximum Mean Discrepancy for Likelihood-Free Inference
Likelihood-free inference methods typically make use of a distance between simulated and real data. A common example is the maximum …
Ayush Bharti
,
Masha Naslidnyk
,
Oscar Key
,
Samuel Kaski
,
François-Xavier Briol
Cite
Code
arXiv
Robust and Scalable Bayesian Online Changepoint Detection
This paper proposes an online, provably robust, and scalable Bayesian approach for changepoint detection. The resulting algorithm has …
Matias Altamirano
,
François-Xavier Briol
,
Jeremias Knoblauch
Cite
Code
arXiv
«
»
Cite
×