Lightnews — Scholar-powered news

Joel Dyer

@joelnmdyer.bsky.social

780 followers 170 following 13 posts

AI/ML Research Scientist @compscioxford.bsky.social & @inetoxford.bsky.social Website: https://joelnmdyer.github.io GitHub: https://github.com/joelnmdyer

joelnmdyer.github.io

Posts Media Videos Starter Packs

Pinned

Joel Dyer @joelnmdyer.bsky.social · Jun 26

We’ve got a new paper out on “Learning Likelihood-free Reference Priors”, forthcoming at #ICML2025.

In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵

Reposted by Joel Dyer

Thomas House @tah-sci.com · Aug 2

There can be no better example of something deeply wrong with this country's national culture than the normalisation of the description of a soggy pre-packaged sandwich as a "main".

Joel Dyer @joelnmdyer.bsky.social · Jun 26

Check out the paper below, or come chat to us in Vancouver for more details!

Paper: lnkd.in/eHjtXYbx

#AI4Science #Bayes #ICML #simulation

Joel Dyer @joelnmdyer.bsky.social · Jun 26

We propose and compare two ways to learn RPs for arbitrary simulation models using neural mutual information estimators, showing that these approaches can accurately recover known reference priors and provide a way to subsequently perform neural simulation-based Bayesian inference *for free*.

Joel Dyer @joelnmdyer.bsky.social · Jun 26

Finding reference priors is difficult, however – this is especially true for simulation models, which are used across scientific domains (particle physics simulators in physics, agent-based models in economics, etc.).

Joel Dyer @joelnmdyer.bsky.social · Jun 26

This is measured by a KL divergence between the posterior and prior. The idea is that these priors provide a means to conduct prior sensitivity analyses, allowing modellers to measure how much prior information is incorporated into their Bayesian procedures through the prior distribution they chose.

Joel Dyer @joelnmdyer.bsky.social · Jun 26

RPs were developed as one possible way to formalise the notion of “minimal prior information” in Bayesian inference, and are priors that maximise the expected information to be gained from data about the model’s parameters.

Joel Dyer @joelnmdyer.bsky.social · Jun 26

We’ve got a new paper out on “Learning Likelihood-free Reference Priors”, forthcoming at #ICML2025.

In this paper, we consider how reference priors (RPs) can be constructed for arbitrary simulation models. 🧵

Reposted by Joel Dyer

Riccardo @rmassidda.it · May 19

🔥 Got a great work on causal representation learning, abstraction, high-dimensional discovery, or other hot topics in causality?

🇧🇷 Don’t miss your chance to present in Rio at the CAR Workshop at #UAI2025!

⏰ Deadline is in 1 week – May 26!
🌐 sites.google.com/view/car-25/

Causal Abstractions and RepresentationsWorkshop @ UAI 2025July 25th 2025, Rio de Janeiro 🇧🇷

sites.google.com

Reposted by Joel Dyer

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · May 19

Going to the hospital because I broke my wrist smashing the endorse button:
www.understandingai.org/p/i-got-fool...

I got fooled by AI-for-science hype—here's what it taught me

I used AI in my plasma physics research and it didn’t go the way I expected.

www.understandingai.org

Reposted by Joel Dyer

Tyler, from the Internet @tylerfromtheinternet.com · May 15

Lmao

How the web became unreadable, an article obscured by medium's pop up asking you to sign up to read the words that have already loaded.

Reposted by Joel Dyer

Janelle Shane @janelleshane.com · Apr 12

1. LLM-generated code tries to run code from online software packages. Which is normal but
2. The packages don’t exist. Which would normally cause an error but
3. Nefarious people have made malware under the package names that LLMs make up most often. So
4. Now the LLM code points to malware.

David D. Levine @daviddlevine.com · Apr 12

LLMs hallucinating nonexistent software packages with plausible names leads to a new malware vulnerability: "slopsquatting."

LLMs can't stop making up software dependencies and sabotaging everything

: Hallucinated package names fuel 'slopsquatting'

www.theregister.com

Reposted by Joel Dyer

CompSciOxford @compscioxford.bsky.social · Apr 3

Professor Nigel Shadbolt has shared his thoughts on the potential risks of AI-powered teddy bears that use AI to converse with children. He suggested that they 'could be used to survey, they could be used to appropriate and harvest data from the child.' www.telegraph.co.uk/news/2025/03...

AI teddies could ‘harvest data from your children’

Sir Nigel Shadbolt, a leading researcher, has raised concerns about ‘smart toys’

www.telegraph.co.uk

Reposted by Joel Dyer

Mencap @handle.invalid · Mar 28

1/1🗣️People with a learning disability die up to 20 years younger than the general population, even though this could be avoided with the right healthcare.

Mencap campaigners posing next to posters in the Westminster tube station. The text says "People with a learning disability die, on average, up to 20 years younger than the general population, even though this could be avoided with the right healthcare."

Mencap campaigners posing next to posters in the Westminster tube station. The text says "People with a learning disability die, on average, up to 20 years younger than the general population, even though this could be avoided with the right healthcare."

Reposted by Joel Dyer

Institute for New Economic Thinking, Oxford @inetoxford.bsky.social · Mar 21

🆕 Agent Based Modelling Comes of Age
@doynefarmer.bsky.social believes creating economic models that can make useful predictions may be the most important problem in economics today
🔖We summarise 3 of 2025's ground breaking papers
🔗https://www.inet.ox.ac.uk/news/agent-based-modelling-comes-of-age

Agent Based Modelling Comes of Age

Our recently published research demonstrates how ABMs is 'coming of age' cross three areas: central banking, economics and finance, and AI.

www.inet.ox.ac.uk

Reposted by Joel Dyer

François-Xavier Briol @fxbriol.bsky.social · Jan 28

Excited to announce we are organising a two-day workshop on 'Bayesian Computation and Inference in Misspecified Models' at BayesComp 2025!

Registrations are now open, with a very nice lineup of speakers to be announced soon! bayescomp2025.sg

@isba-bayesian.bsky.social

Bayes Comp 2025

bayescomp2025.sg

Reposted by Joel Dyer

Mencap @handle.invalid · Jan 27

We’re overwhelmed by all the generous donations from Traitors fans after hearing Alexander Dragonetti’s story! 🎉

You’d wanted to know how much has been raised...

#TheTraitors #AlexanderDragonetti

Reposted by Joel Dyer

Vincent Fortuin @vincefort.bsky.social · Jan 24

Definitely consider submitting your work to UAI, it's fantastic conference!

And while you're at it, why not submit a shorter version to the AABI workshop track (deadline Feb 7)? 😉

Sara Magliacane @smaglia.bsky.social · Jan 23

Sad after #AISTATS2025 and #ICLR2025 notifications? As we say in Italy, when a door closes, a bigger one opens ;)

If you have a fantastic paper on #uncertainty #AI #ML #causality #statML #probabilisticmodels #reasoning #impreciseprobabilities etc, consider submitting to #UAI2025 🇧🇷 deadline 10 Feb 💥

uai2025 @auai.org · Dec 3

The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25!

The CfP is out 👉 www.auai.org/uai2025/call...

🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification

#UAI2025 #ML #stats #learning #reasoning #uncertainty

Reposted by Joel Dyer

Aleksander Molak @alxndrmlk.bsky.social · Jan 24

#UAI is one of the best general conferences for causal researchers

Submission deadline: Feb 10

#CausalSky

Sara Magliacane @smaglia.bsky.social · Jan 23

Sad after #AISTATS2025 and #ICLR2025 notifications? As we say in Italy, when a door closes, a bigger one opens ;)

If you have a fantastic paper on #uncertainty #AI #ML #causality #statML #probabilisticmodels #reasoning #impreciseprobabilities etc, consider submitting to #UAI2025 🇧🇷 deadline 10 Feb 💥

uai2025 @auai.org · Dec 3

The 41st Conference on #Uncertainty in #AI will be held in Rio de Janeiro 🇧🇷, July 21-25!

The CfP is out 👉 www.auai.org/uai2025/call...

🚨 Feb 10: Paper submission
🗣️ Apr 3-10: rebuttal period
🎉/💀 May 6: Author notification

#UAI2025 #ML #stats #learning #reasoning #uncertainty

Reposted by Joel Dyer

↑Lionel Yelibi↓ @spiindoctor.bsky.social · Nov 12

✨I made a starter pack for complexity scientists on this platform.✨

go.bsky.app/QzMwdrL

Reposted by Joel Dyer

Yorgos @yfelekis.bsky.social · Dec 7

Next week will be ✈️to @neuripsconf.bsky.social together with @joelnmdyer.bsky.social and Nick Bishop to present our work on "Interventionally Consistent Surrogates for Complex Simulation Models". Details 👇

Joel Dyer @joelnmdyer.bsky.social · Dec 7

@neuripsconf.bsky.social

Joel Dyer @joelnmdyer.bsky.social · Dec 4

@inetoxford.bsky.social @inet-complexity.bsky.social @compscioxford.bsky.social #causal #simulation #Bayes

Reposted by Joel Dyer

Ewan Colman @ewancolman.bsky.social · Nov 29

2 weeks left to apply for this PhD position (link at end of thread) #EpiSky #IDSky

Ewan Colman @ewancolman.bsky.social · Nov 24

Which infectious disease will dominate the headlines in the coming years? A new emerging disease? Outbreaks of mpox or ebola? An endemic disease like malaria?

Or, it could be a resurgent disease - something once downgraded as a public health hazard that makes a come-back. Some examples:

A graph of an epidemic over time with emergence, early outbreak, endemicity, interventions, and resurgence, labelled at relevant points along the line

Joel Dyer @joelnmdyer.bsky.social · Nov 27

2) “Model Exploration through Marginal Likelihood Entropy Maximisation”, accepted at the #NeurIPS2024 D3S3 Workshop. We propose a method for exploring the behaviours a (differentiable) simulator can generate – useful for understanding your mechanistic model! openreview.net/pdf?id=dPszK... (3/3)

Joel Dyer @joelnmdyer.bsky.social · Nov 27

This provides decision- and policy-makers with a way to reduce the cost of running simulations when designing policies and interventions. Useful in time-critical settings, such as emerging pandemics! (2/3)