Kevin Murphy (Google DeepMind) will come to visit us next Monday and give a seminar. See details and Zoom link below: Speaker:  Kevin Murphy Title: The 4 pillars of machine learning: Predictions, Decisions, Analysis, Synthesis Date: Monday 13th of November between 13:00-14:00

We are excited to have Kevin Patrick Murphy speak to us next Monday (13th of November)! If you're at UCL, join us in person! Otherwise, find details & a zoom link below :)

Interested in Gaussian process regression and/or generalised Bayes? I will be presenting this recent paper showing how to make GPs both outlier-robust and scalable tomorrow at #BAYSM2023 (session starting at at 3.30pm UK-time). j-ISBA Jeremias Knoblauch Matias Altamirano Montero.

Get in touch if you'd like to join a young and vibrant community working at the intersection of machine learning & statistical sciences! Happy to walk you through what you could expect if you joined us :)

A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods [oral], with Veit D. Wild, Sahra Ghalebikesabi, Jeremias Knoblauch, links variational inference, Wasserstein gradient flows and deep ensembles in a new and insightful way. arxiv.org/abs/2305.15027 neurips.cc/virtual/2023/o… 2/4

With some notable exceptions, the reviews I saw for AISTATS both as Area Chair & as author this year have been of almost insultingly low quality. 🫤 Don't really know what to do about it, and hoping that this is just down to a very noisy signal.

If you are a non-UK researcher interested in stats/ML & in joining us at UCL with 2 years of independent funding to help start your own group, get in touch with me! The Newton International Fellowships have just opened! royalsociety.org/grants-schemes…

📢 I am looking for 2 postdocs in my ERC project NEMESIS (tinyurl.com/4d2ry2vj) to develop advanced statistical models for complex (criminal 🕵️) networks‼️ Deadline: April 30, 2024 Duration: 1 year, renewable Where: BIDSA Università Bocconi Info-Application: jobmarket.unibocconi.eu/?id=574

We have a new webpage for the "fundamentals of statistical machine learning"research group at UCL Statistical Science: fsml-ucl.github.io. Check it out to find out what we have been up to! Jeremias Knoblauch Matias Altamirano Montero Masha Naslidnyk Ieva Kazlauskaite UCL

What if a generalised posterior / Gibbs measure uses a loss that need to be estimated? This happens often, e.g. for posteriors based on the MMD, beta-divergences, & estimated likelihoods. Me, David T. Frazier, & Chris Drovandi answer this in a new paper: arxiv.org/abs/2404.15649

We have a faculty position coming up; get in touch/PM me if you'd like to join us at UCL! Deadline 28th of August. Compensation substantially higher than listed (can give details per PM)

Matias Altamirano Montero will present two papers at ICML Conference on how generalised Bayes can make probabilistic ML robust and scalable. Say hi to him! Spotlight paper on GPs -Wed HallC 4-9 #1506: arxiv.org/abs/2311.00463 Paper on KF -Tues HallC 4-9 #1602: arxiv.org/abs/2405.05646 Jeremias Knoblauch

Applications are invited for 1 PhD Studentship (UK fee only) based at the Department of Statistical Science, University College London. The position can involve any topic within the Statistical Science remit. Deadline for applications: 16 August 2024 ucl.ac.uk/statistics/pro…

Friends, I'm excited to share some professional news: - I'll be promoted to Associate Professor in October - my research won the Savage Award (tinyurl.com/pvm6vpfk) - I've started working at the nexus of ML & consumer/human rights with FoxGlove (NGO) and Leigh Day (law firm)