Lightnews — Scholar-powered news

Adrien Corenflos @adriencorenflos.bsky.social · 5h

As a large language model developed by OpenAI, I don't have genitals. Would you like to hear me apologising instead?

The Verge @theverge.com · 18h

Sam Altman says ChatGPT will soon sext with verified adults

ChatGPT is about to get flirty.

buff.ly

1

Adrien Corenflos @adriencorenflos.bsky.social · 20h

Oh? This looks pretty aligned to my interests!

Adrien Corenflos @adriencorenflos.bsky.social · 2d

Most joint distributions can't cleanly be expressed as the divergence of a vector field (especially in dimensions > 2) so this doesn't apply. Also, you usually don't care about the probability of an event, but rather about an expected outcome under this event. Makes it even less relevant.

1

Adrien Corenflos @adriencorenflos.bsky.social · 2d

Found the paper
arxiv.org/abs/2010.01709

Instead of Rewriting Foreign Code for Machine Learning, Automatically Synthesize Fast Gradients

Applying differentiable programming techniques and machine learning algorithms to foreign programs requires developers to either rewrite their code in a machine learning framework, or otherwise provid...

arxiv.org

3

Adrien Corenflos @adriencorenflos.bsky.social · 2d

Thankfully that's not the current approach! People (shout-out to them!) are working on automatic diffentiation of pre-existing low-level numerical code.

github.com/EnzymeAD/Enz...

Typically targets an intermediate representation that's universally used (incl Fortran)

en.wikipedia.org/wiki/LLVM

GitHub - EnzymeAD/Enzyme: High-performance automatic differentiation of LLVM and MLIR.

High-performance automatic differentiation of LLVM and MLIR. - EnzymeAD/Enzyme

github.com

2 1 2

Adrien Corenflos @adriencorenflos.bsky.social · 2d

This was published in 2022? 😯

1

Reposted by Adrien Corenflos

ArXiv Paperboy (Stat.ME+Econ.EM) @paperposterbot.bsky.social · 4d

link 📈🤖
A coupling-based approach to f-divergences diagnostics for Markov chain Monte Carlo (Corenflos, Dau) A long-standing gap exists between the theoretical analysis of Markov chain Monte Carlo convergence, which is often based on statistical divergences, and the diagnostics used in practice.

1 4

Reposted by Adrien Corenflos

Adam Johansen @adamjohansen.bsky.social · 22d

There are a couple of vacancies in Wollongong for Maths/Stats lecturers:

www.uow.edu.au/about/jobs/j...

www.uow.edu.au

4 3

Reposted by Adrien Corenflos

Sam Power @spmontecarlo.bsky.social · 25d

The first talk of the season will be this coming Tuesday (23 September), given by Alexandre Bouchard-Côté from UBC. Alex is a great speaker, so do join if you have the chance!

See sites.google.com/view/monte-c... for details, links, and so on.

1 5 17

Adrien Corenflos @adriencorenflos.bsky.social · Sep 5

It's clearly a technological feat, no question there, but robotaxi is also a misplaced (and somewhat detrimental) effort. A dense integrated public transport simply seems overall better for the majority (some of it may very well be self-driving buses/minibuses!)

Reposted by Adrien Corenflos

Sam Duffield @samduffield.com · Aug 29

New paper on arXiv! And I think it's a good'un 😄

Meet the new Lattice Random Walk (LRW) discretisation for SDEs. It’s radically different from traditional methods like Euler-Maruyama (EM) in that each iteration can only move in discrete steps {-δₓ, 0, δₓ}.

1 5 16

Adrien Corenflos @adriencorenflos.bsky.social · Aug 28

Hold on, I was convinced yours was pronounced Sam Pouvoir???

5

Adrien Corenflos @adriencorenflos.bsky.social · Aug 28

I do this too. I call it the email sandwich. Sometimes I only answer in the morning, and then I call it the email tartine.

3

Adrien Corenflos @adriencorenflos.bsky.social · Aug 26

This gives Greek Stochastics vibes.

1 1

Adrien Corenflos @adriencorenflos.bsky.social · Aug 18

"Who is seldom accused of cheer with respect to anything" 😂😂😂

Please keep your compliments where I can see them.

2

Adrien Corenflos @adriencorenflos.bsky.social · Aug 16

📌

1

Adrien Corenflos @adriencorenflos.bsky.social · Aug 16

You might like this
en.m.wikipedia.org/wiki/Penrose...

Penrose graphical notation - Wikipedia

en.m.wikipedia.org

1

Adrien Corenflos @adriencorenflos.bsky.social · Aug 16

E.g. arxiv.org/abs/2112.12908?

Annealed Leap-Point Sampler for Multimodal Target Distributions

In Bayesian statistics, exploring high-dimensional multimodal posterior distributions poses major challenges for existing MCMC approaches. This paper introduces the Annealed Leap-Point Sampler (ALPS),...

arxiv.org

1 1

Adrien Corenflos @adriencorenflos.bsky.social · Aug 15

Someone had way too much fun writing this ☺️

1 1

Adrien Corenflos @adriencorenflos.bsky.social · Aug 11

Applied mechanics

3

Reposted by Adrien Corenflos

Adam Johansen @adamjohansen.bsky.social · Aug 6

Applications are still open for another two weeks.

Adam Johansen @adamjohansen.bsky.social · Jul 23

If anyone is, or knows anyone who is, looking for a postdoc position to work on the foundations of scalable inference and such... applications for a postdoctoral position at Warwick as a part of the OCEAN project (oceanerc.com) are open until 20th August at warwick-careers.tal.net/vx/appcentre....

OCEAN

OCEAN is an ERC Synergy grant gathering researchers to lay the fundations of the next-generation machine learning algorithms, involving decentralized inference and predictive tasks in the presence …

oceanerc.com

2 2

Adrien Corenflos @adriencorenflos.bsky.social · Jul 26

The physics talks had a lot of this + misspecification

1

Reposted by Adrien Corenflos

Sam Power @spmontecarlo.bsky.social · Jul 26

Prepping my post-BayesComp "stock market update" (to be taken with a pinch of salt!) on how different topics fared relative to my expectations / past years.

1 2 27

Adrien Corenflos @adriencorenflos.bsky.social · Jul 25

It was great hanging out! Let's do it in the UK too :D

1

Reposted by Adrien Corenflos

Sam Power @spmontecarlo.bsky.social · Jul 24

I am pleased to announce that together with some friends, we are organising a workshop on Non-Reversible MCMC Sampling, taking place at Newcastle University from 8–10 September 2025.

Details on the programme and registration can be found at the workshop website (sites.google.com/view/probai-...).

2 12 31