François-Xavier Briol
@fxbriol.bsky.social
Professor of Statistics and Machine Learning at UCL Statistical Science. Interested in computational statistics, machine learning and applications in the sciences & engineering.
Thanks Robin! And of course your very nice review of ABC was very helpful (and can be found in the references for those interested!).
August 28, 2025 at 4:35 PM
Thanks Robin! And of course your very nice review of ABC was very helpful (and can be found in the references for those interested!).
Thanks for the interest! I'll send you a separate copy without the breaks via email, but I don't think it'll be better because I tend to make various parts of the slide appear/disappear, so removing breaks will make things look very messy.
August 28, 2025 at 4:35 PM
Thanks for the interest! I'll send you a separate copy without the breaks via email, but I don't think it'll be better because I tend to make various parts of the slide appear/disappear, so removing breaks will make things look very messy.
Well done again to @hudsonchen.bsky.social on his very first ICML paper! 😎
May 8, 2025 at 4:29 AM
Well done again to @hudsonchen.bsky.social on his very first ICML paper! 😎
Surprisingly, @hudsonchen.bsky.social was able to prove a very fast convergence rate! He showed an interpolation rate whereas it was previously believed that only a much slower noisy regression rate was feasible! 🤯
This improves on our prior work: arxiv.org/abs/2406.16530 and all competing methods.
This improves on our prior work: arxiv.org/abs/2406.16530 and all competing methods.
Conditional Bayesian Quadrature
We propose a novel approach for estimating conditional or parametric expectations in the setting where obtaining samples or evaluating integrands is costly. Through the framework of probabilistic nume...
arxiv.org
May 8, 2025 at 4:29 AM
Surprisingly, @hudsonchen.bsky.social was able to prove a very fast convergence rate! He showed an interpolation rate whereas it was previously believed that only a much slower noisy regression rate was feasible! 🤯
This improves on our prior work: arxiv.org/abs/2406.16530 and all competing methods.
This improves on our prior work: arxiv.org/abs/2406.16530 and all competing methods.
Our paper remedies the problem with a very simple algorithm which is a nesting of two kernel quadrature algorithms. This provably reduces the number of samples needed to obtain a given accuracy when the problem isn't too high dimensional and smooth.
May 8, 2025 at 4:29 AM
Our paper remedies the problem with a very simple algorithm which is a nesting of two kernel quadrature algorithms. This provably reduces the number of samples needed to obtain a given accuracy when the problem isn't too high dimensional and smooth.
Unfortunately, existing methods such as nested Monte Carlo or multilevel Monte Carlo require a huge number of samples at each level of nesting to estimate these accurately! ☹️
May 8, 2025 at 4:29 AM
Unfortunately, existing methods such as nested Monte Carlo or multilevel Monte Carlo require a huge number of samples at each level of nesting to estimate these accurately! ☹️
Why should you care? Nested expectations are a significant computational challenge in stats/ML: they arise in active learning, Bayesian optimisation, experimental design, but also other fields such as option pricing and health economics.
May 8, 2025 at 4:29 AM
Why should you care? Nested expectations are a significant computational challenge in stats/ML: they arise in active learning, Bayesian optimisation, experimental design, but also other fields such as option pricing and health economics.
Huge congrats to William Laplante (williamlaplante.github.io) on his first paper, completed in the first few months of his PhD!
And thanks to all collaborators including
@maltamiranomontero.bsky.social, Andrew Duncan and Jeremias Knoblauch.
And thanks to all collaborators including
@maltamiranomontero.bsky.social, Andrew Duncan and Jeremias Knoblauch.
William Laplante
williamlaplante.github.io
May 6, 2025 at 8:33 AM
Huge congrats to William Laplante (williamlaplante.github.io) on his first paper, completed in the first few months of his PhD!
And thanks to all collaborators including
@maltamiranomontero.bsky.social, Andrew Duncan and Jeremias Knoblauch.
And thanks to all collaborators including
@maltamiranomontero.bsky.social, Andrew Duncan and Jeremias Knoblauch.
The paper builds on the robust and scalable Gaussian process (RCGP) algorithm from our ICML 2024 paper (arxiv.org/abs/2311.00463). It shows that it can make use of common computational tricks in spatio-temporal settings, and also uses adaptive hyper parameter optimisation to improve calibration.
Robust and Conjugate Gaussian Process Regression
To enable closed form conditioning, a common assumption in Gaussian process (GP) regression is independent and identically distributed Gaussian observation noise. This strong and simplistic assumption...
arxiv.org
May 6, 2025 at 8:33 AM
The paper builds on the robust and scalable Gaussian process (RCGP) algorithm from our ICML 2024 paper (arxiv.org/abs/2311.00463). It shows that it can make use of common computational tricks in spatio-temporal settings, and also uses adaptive hyper parameter optimisation to improve calibration.
Thanks Pierre! I think it could be quite handy for MMD-Bayes and MMD estimators :).
April 29, 2025 at 7:36 AM
Thanks Pierre! I think it could be quite handy for MMD-Bayes and MMD estimators :).
We also have excellent line-up of invited speakers which includes @pierrealquier.bsky.social, @eweinstein.bsky.social, Jeremias Knoblauch, David Frazier, Harita Dellaporta, Antonietta Mira, Jeremie Houssineau, Sonia Petrone, Edwin Fong and Aretha Teckentrup.
April 2, 2025 at 3:04 PM
We also have excellent line-up of invited speakers which includes @pierrealquier.bsky.social, @eweinstein.bsky.social, Jeremias Knoblauch, David Frazier, Harita Dellaporta, Antonietta Mira, Jeremie Houssineau, Sonia Petrone, Edwin Fong and Aretha Teckentrup.