Layer-wise equivariance symmetries (e.g. conv layers) allow neural nets to generalise effectively. But can we learn them automatically using gradients? We show we can! Excited to share that our method ELLA has been accepted as a spotlight paper at #neurips2023. A thread.👇1/11🧵

Great to see Tycho's progress on taking inspiration from Bayesian model selection to search over NN architectures! Do check out his thread.

Learning Layer-wise Equivariances Automatically using Gradients (Awarded spotlight) Join us for our poster this Wednesday at 5pm! As they'd say here in New Orleans, I am very keen to meet 'all y'all' and talk about research. Let's discuss learning symmetry and inductive bias.

The pressure is real. But strongly agree that fewer papers that deeply investigate a question and link to existing understanding is more productive. I have seen hiring panels appreciate this! Having developed your own ideas is more valuable than just having your name on a paper.

An interesting concrete suggestion for a mechanism to encourage voluntarily cooperation to reduce greenhouse gas emissions. If we can agree that climate change has a cost, then perhaps we can agree on a CO2 price, if only we had the right mechanism.

Late announcement, but I'm excited to announce that my PhD thesis is publicly available! In it I give my thoughts on how to approach variational inference in Bayesian neural nets, deep GPs, including discussion on the marginal likelihood and symmetries. arxiv.org/abs/2401.12418

Our paper, "The LLM Surgeon," accepted at ICLR 2024, achieves SOTA in LLM pruning in all unstructured, semi-structured, and the most challenging but most effective structured pruning that removes entire matrix rows/columns. Happy to share that code is now publicly available.

Build what you need and use what you build. This is a core philosophy of my research. It shifts the focus away from publishing “papers” to what really matters — impact. This thread unpacks why I think this is a successful approach to science. 1/10 Or see: perceiving-systems.blog/en/post/build-…

Great internship project by Tycho and his Qualcomm collaborators!

We have an opportunity for outstanding mid-career researchers (typically 10-20 years from PhD) to apply for a The Royal Society Faraday Discovery Fellowship at the department. Learn more here: cs.ox.ac.uk/news/2349-full… #compscioxford

A Gaussian Process regression model built on top of protein language model embeddings and inverse folding models makes accurate predictions with calibrated uncertainties. Wouter Boomsma

Looking forward to #GenU2024, my favourite gathering in the AI/ML calendar. The talks again all look incredibly interesting!