Just a reminder that we're still hiring for parser/compiler-related work and more: jobs.ashbyhq.com/dottxt

My fantastic co-authors Desi (Desi R. Ivanova) and Stefan (Stefan Radev) will present our paper on data-efficient amortized inference at #ICML2024 ✨ You can find them on Thursday from 13:30–15:00 in Hall C 4-9 at poster #1305. More info in Desi‘s thread below 🧵👇

We have a spotlight paper at #ICML2024 on batch and match: black box variational inference with a score-based divergence. Our poster is Thursday 11:30a Hall C 4–9 #1307. 1/n

also, check out this other work on the topic of generative flow networks by Tiago da Silva Tiago da Silva et al. x.com/wkly_infrmtive…

We're seeking a dedicated student researcher to work on groundbreaking #LLM alignment research this fall. This position requires a minimum 80% appointment, and we strongly encourage working from office. If you're passionate about advancing AI safety, please DM me with your

We uploaded a v2 of our book draft "The Elements of Differentiable Programming" with many improvements (~70 pages of new content) and a new chapter on differentiable data structures (lists and dictionaries). arxiv.org/abs/2403.14606

We shipping. Expect dispatch on model name and support of chat templates soon (already implemented by a community member in a separate repo). github.com/outlines-dev/p…

And finally this is out. How to make factor analysis and multi-study factor analysis very fast with Blake Hansen, Alejandra Avalos Massimiliano Russo Brown Biostatistics Brown Data Science Institute tandfonline.com/doi/abs/10.108…

Roberta DeVito Conor Hassan Massimiliano Russo Brown Biostatistics Brown Data Science Institute Miracle of the day: Blake is here!!!!🎉🎉🎉

Warwick PhD wins international award Jeremias Knoblauch has been awarded the 2023 Savage Award of the International Society for Bayesian Analysis for his Warwick PhD thesis “Optimization-centric Generalizations of Bayesian Inference” supervised by Theo Damoulas.

Our very own Dr Samuel Livingstone is on the Spotlight in the latest issue of the UCL Mathematical & Physical Sciences newsletter! Find out more about Sam at: ucl.ac.uk/mathematical-p…

Roberta DeVito Conor Hassan Massimiliano Russo Brown Biostatistics Brown Data Science Institute Blake Wrong one... Oops! This is THE one Blake Hansen Damn you dislexia!

For too long, users have lived under the software lottery tyranny of fused attention implementations. No longer. Introducing FlexAttention, a new PyTorch API allowing for many attention variants to enjoy fused kernels in a few lines of PyTorch. pytorch.org/blog/flexatten… 1/10

As promised I wrote an analysis about the cost of function calls, builtin calls and inlined code in Python using microbenchmarks. I explain in detail what recent changes in CPython have improved the perf in these areas and how. I try to connect the dots between the slow parts

Machine learning postdoc positions in my team in Helsinki, Finland, and Manchester, UK; DL September 15, 2024 Aalto University, Helsinki: aalto.fi/en/open-positi… University of Manchester, UK: jobs.manchester.ac.uk/Job/JobDetail?… Some more info about the team: kaski-lab.com

The answer: pass in `dim` as an argument and define it outside the JIT-compilation!

Our #ELLISUnit Helsinki students representing this week at #EDS2024 🙌 ELLIS Yifan Zhu Antti Honkela Samuel Kaski Faculty of Science, University of Helsinki Computer Science

Next Thursday, Sept. 12: Seminar on Advances in Probabilistic Machine Learning returns, with Thomas Möllenhoff: Variational Learning is Effective for Large Deep Networks. Register here for the Zoom link: aaltoml.github.io/apml/ cc Arno Solin Computer Science Computer Science @ University of Helsinki RIKEN Center for Advanced Intelligence Project

Last week to apply for machine learning postdoc positions in my team in Manchester or Helsinki

We have two open post-doc positions. You dont' have to be a Bayesian but somebody who is interested to work with at the intersection of DL, Bayes, and optimization. riken.jp/en/careers/res… Interest in understanding deep learning and continual lifelong learning is a plus!