🔥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

Richard Turner and colleagues from Cambridge University Cambridge MLG ETH Zurich put together a very interesting piece of work on Gaussian Processes and Variational autoencoders, namely "Sparse Gaussian Processes Variational Autoencoders" arxiv.org/pdf/2010.10177… I highly recommend it!

PhD positions in Machine Learning at Cambridge. Please apply by Dec 3! Opportunities to work with me on trustworthy ML including fairness, interpretability and robustness. Feel free to get in touch if you have questions.

If you want to endow your (awesome) VAEs with (even more awesome) Gaussian Processes, have a look at our new AISTATS paper (arxiv.org/abs/2010.13472) where we present a scalable version of such models! More info in thread. 1/7

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

Sharing an RA opportunity to collaborate on explainability w/ Frens Kroger, Beate Grawemeyer, jeff hancock, and me. We're looking to study trust formation via transparency and its relation to online harms. bit.ly/3iKTRri

I'm excited to announce that I'm going to begin my graduate studies this fall at Psychology at Edinburgh, exploring the neural mechanisms of theory of mind development with Hilary Richardson @hilaryrichardson.bsky.social, funded by SGSSS.

PhD student Umang Bhatt awarded a J.P. Morgan AI #PhD #Fellowship Umang works to ensure that machine learning technologies are developed responsibly. As #AI makes ever more decisions in our lives, his research is incredibly important. eng.cam.ac.uk/news/phd-stude… St Edmund's College, Cambridge

With deep gratitude and appreciation to amazing collaborators at Cambridge University The Alan Turing Institute @CDEIUK Future Intelligence Cambridge MLG Engineering Dept Cambridge Computer Science and beyond. And congratulations to all other recipients including Prof Marion Oswald, MBE !

I think the Cambridge MLMI MPhil is among the best and most competitive in Europe. We're looking for someone to help run the taught component! Job opportunity: Associate Teaching Professor at the University of Cambridge, Department of Engineering Advert: jobs.cam.ac.uk/job/35215/

I’m excited to to share our #NeurIPS2022 Causal ML Challenge organised by Microsoft Research and |= Eedi. Participants discover causal relations between learning constructs in synthetic and real data. Kudos to WenboGong for setting it up. Please join: codalab.lisn.upsaclay.fr/competitions/5…

If you're at #ICML2022, check out our poster “Perspectives on Incorporating Expert Feedback into Model Updates” at the Updatable ML workshop in Ballroom 2 tomorrow at 3:30pm. 🧵 Joint w/ Valerie Chen, Hoda Heidari, Adrian Weller, Ameet Talwalkar Preprint: arxiv.org/abs/2205.06905

I'm happy to share more information about our #NeurIPS2022 workshop on Causal ML for real-world impact. Please submit short papers until Sept, 30th and join us in New Orleans on Dec, 2nd. You can find more information and CfP here: cml-4-impact.vanderschaar-lab.com

Thank you NeurIPS Conference for a great birthday present: 0 out of 1 papers accepted! #NeurIPS2022

PhD opportunities at the Cambridge Machine Learning Group Cambridge MLG. Application deadline 1 Dec at noon (UK time). More info at mlg.eng.cam.ac.uk/phd_programme_…

“This looks like the funny numbers you make on your laptop!!”

I successfully defended my PhD thesis today 🎉 Many thanks to my examiners, Eric Horvitz and Neil Lawrence, for their thoughtful comments and a very fun viva!

Adrian Weller Adrian Weller (mlg.eng.cam.ac.uk/adrian/), who has broad interests across trustworthy AI including explainability, fairness, robustness, scalability, privacy, safety, and ethics.

Approximately Equivariant Neural Processes. arxiv.org/abs/2406.13488

Gridded Transformer Neural Processes for Large Unstructured Spatio-Temporal Data ift.tt/4NfnSjm

Indeed! now accepted at TMLR openreview.net/forum?id=L33DS…. Also check out Titsias’ concurrent paper.