🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Interested in linear models and probabilistic programming? Then check out our post on linear models from a Gaussian process point of view with Stheno and JAX! wesselb.github.io/2021/01/19/lin… invenia.github.io/blog/2021/01/1…

We have openings for 2 postdoc positions in our group (closing date: 28 January) -- looking forward to your applications! Thanks for retweeting! jobs.cam.ac.uk/job/28154/

Got questions about approximate inference quality in Bayesian neural nets? Come along to our joint Zoom talk/discussion! 😀

Cambridge MLG is launching a blog, featuring a first two-part post about what keeps a Bayesian awake at night by Richard E. Turner and me. 🧵 mlg-blog.com

Did you miss our second Cambridge University ELLIS Unit seminar in Engineering Dept with Prof. Richard Turner, a leading researcher in the area of #machinelearning and #AI. Please see the seminar here: youtube.com/watch?v=70n5cA…

Still using latent variables to get correlations out of your Neural Process? Then consider Gaussian Neural Processes (GNP)! ✓ Correlated predictions ✓ Tractable likelihood Stratis Markou, James Requeima, Wessel, Anna Vaughan & Rich Turner #ICLR2022 arxiv.org/abs/2203.08775

Yann LeCun Yes ok, but why do they have to shout so much while they're learning?

📢Thrilled to be presenting 'Environmental Sensor Placement with Convolutional Gaussian Neural Processes' at a #NeurIPS22 workshop 🗞️Poster gp-seminar-series.github.io/neurips-2022/a… 📰Paper arxiv.org/abs/2211.10381 🤝Collaboration betw British Antarctic Survey 🐧 & Cambridge MLG 💲Funded by The Alan Turing Institute 👇More below

I should have announced this before, but a year ago I switched my research focus to AI existential risk reduction and governance. I think the risk of bad outcomes for humanity due to AGI is substantial, and that coordinating a slowdown in AGI development is probably a good idea.

I'm very excited to announce the release of Plum 2.0! With this release, Plum is fully powered by Beartype, which means that Plum now supports any type supported by Beartype. And that's not all: Plum is now proudly a member of the Beartype org! github.com/beartype/plum

Great presentation from Tom Andersson on day 2 Climate Informatics 🎉 Active learning improve how we understand the Antarctic. Impressive work. See the paper here: arxiv.org/abs/2211.10381

Happy to announce our #ICLR2023 paper Autoregressive Conditional Neural Processes! w/ Stratis Markou, James Requeima, Andrew Foong, Tom Andersson, Anna Vaughan, Anthony Buonomo, @scotthosking, Rich Turner Paper: arxiv.org/abs/2303.14468 Code: github.com/wesselb/neural… 🧵1/4

QUIZ: One of these plots shows temperature around Antarctica. The others are samples from a model conditioned on obs at the black circles. Which one is the true data? Find it tough? That's the power of the AR ConvCNP. Answer below & check out Wessel's🧵on our #ICLR2023 paper👇

Where should we measure the environment to minimise uncertainty about weather and climate? 🎲⛅ I'm excited to share that my second journal paper, which grapples with this fascinating problem, will be published soon! Interested? Check out my 15-min talk: youtu.be/v0pmqh09u1Y

📢 Excited to announce 'Environmental sensor placement with convolutional Gaussian neural processes', out now in Environmental Data Science Paper: cambridge.org/core/services/… Talk: youtu.be/v0pmqh09u1Y Code: github.com/tom-andersson/… British Antarctic Survey 🐧 Cambridge University The Alan Turing Institute 🧵 1/n

Really excited about this! We've put effort into making the model accessible with code that fits in a Tweet. 😊 pip install microsoft-aurora from aurora import Aurora model = Aurora() model.load_checkpoint("microsoft/aurora", "aurora-0.25-finetuned.ckpt")

(New paper alert!) Forecasting models typically rely on numerical historical data. However, in many cases, numerical data is insufficient and context is key. E.g., In the series below, would you have predicted the drop? Even the best models do not (forecast in blue).

Happy to have been a part of the great team that produced this report!

Understanding causes is key to science. Finite observational data alone isn't enough. While Bayes offers a framework to deal with this, the calculations are often intractable. We introduce a method to accurately approximate the posterior over causal structures. #ICLR2025 🧵1/15