OxCSML

Computational Statistics, Statistical Methodology, and Machine Learning Research Group. Based at @OxfordStats.

[OxCSML @oxcsml]

The OxCSML group @OxfordStats is participating at @NeurIPSConf this
week, with 25 papers in the main program, 3 workshop papers and 1 paper
in dataset track! Do stop by our posters and presentations! Check out https://t.co/R3tJ8o8yTk or the following :thread:for further details

[Freddie Bickford Smith @fbickfordsmith]

Bayes for continual learning: it just works, right?

Turns out the details matter for *approx* Bayes in deep nets.

Variational inference over predictive functions works pretty well!

#ICML2022 paper with @timrudner @qixuan_feng @yeewhye @yaringal

https://t.co/r5qYKFDJKE

1/6

[Tim G. J. Rudner @timrudner]

In our #ICML paper, we show that

*Sequential Function-Space Variational Inference*

allows for effective Bayesian updating in NNs and enables state-of-the-art continual learning!🚀

✍️Paper: https://t.co/ZxuZjlEc3D
💻Code+Notebooks: https://t.co/2KOR0nk65Y

Details in 🧵! [1/N]

[OxCSML @oxcsml]

Congratulations @desirivanova . Well done!

[Isaac Newton Institute @NewtonInstitute]

Congratulations to @desirivanova 🥉 (@OxUniMaths), Matthew Tointon 🥇 (@BristolUniMaths) and Teresa Bautista 🥈 (@KingsCollegeLon) on their @STEM4Brit awards this afternoon! 👏🎉🧮 #mathematics #stem @UKParliament

[Yee Whye Teh @yeewhye]

Applications due this Friday. Please retweet everyone, and please apply if you are a UK undergrad from under-represented backgrounds interested in what research in artificial intelligence and machine learning is like! 🙏

[Oxford Statistics @OxfordStats]

If you're an undergraduate looking for a summer research project in AI or ML - check this out! Up to £4,200 stipend for 10-week project, free accommodation, great projects. Apply by 18 Feb. https://t.co/2fi1n6wcZ1

[Yee Whye Teh @yeewhye]

Oxford's Uniq+ graduate access program has an AI/ML strand! UK undergrads from under-represented backgrounds interested in AI/ML pls apply. Scholarship, free lodging, 6 or 10 weeks summer research project w/ faculty @CompSciOxford @OxfordStats @OxfordEng.

https://t.co/UehniSBrSt

[Valerie Bradley @valeriecbradley]

Excited to share our paper in @Nature today! We find that two large surveys significantly overestimated COVID vaccine uptake among US adults relative to a benchmark from the CDC. Work with @shirokuriwaki @MichaelIsakov3 @sejDino @XiaoLiMeng1 @flaxter https://t.co/dvyo4J1AaP 🧵1/

[OxCSML @oxcsml]

Paper info:

This preliminary work presents the first large-scale study of implicit neural representations with uncertainty quantification. Well-calibrated, accurate image reconstruction algorithms can improve doctor diagnoses and reduce patient radiation exposure.

[OxCSML @oxcsml]

The OxCSML group @OxfordStats is participating at @NeurIPSConf this
week, with 25 papers in the main program, 3 workshop papers and 1 paper
in dataset track! Do stop by our posters and presentations! Check out https://t.co/R3tJ8o8yTk or the following :thread:for further details

[OxCSML @oxcsml]

Uncertainty Quantification in End-to-End Implicit Neural Representations for Medical Imaging
Francisca Vasconcelos, @bobby_he, @yeewhye

Oral at MedNeurIPS: https://t.co/CtrwHNhDY8
Poster at Bayesian Deep Learning Workshop: https://t.co/LzzYTD1vBT
Paper: https://t.co/0AzwAn6HnR