iiinova — where your digital self keeps evolving

Pierre Alquier @pierrealquier.bsky.social · 15h

We uploaded a new version of our mutual information bound for statistical inference with Mehdi: arxiv.org/abs/2412.18539 There are many new results that were not in the previous version, including extentions to misspecified models, etc.

arxiv.org

Convergence of Statistical Estimators via Mutual Information Bounds

Recent advances in statistical learning theory have revealed profound connections between mutual information (MI) bounds, PAC-Bayesian theory, and Bayesian nonparametrics. This work introduces a mut...

0100

Pierre Alquier @pierrealquier.bsky.social · 19h

We are hiring at ESSEC @essecbs.bsky.social (Cergy campus, near Paris). Assistant professor -- econometrics and/or statistics, data analytics. Do not hesitate to contact me or the other members of the group if you have questions. assets.ctfassets.net/vmb6iqn8sgcm...

264

Reposted by Pierre Alquier

Nobel Prize @nobelprize.org · 05/10/2026

BREAKING NEWS The 2026 Nobel Prize in Physiology or Medicine has been awarded to Karl Deisseroth, Peter Hegemann and Georg Nagel “for their discoveries concerning light-gated ion channels and optogenetics.”

231049506

Pierre Alquier @pierrealquier.bsky.social · 19h

Black-naped oriole. I already posted this photo 6 months ago, but I wanted to share it again with the amazing work @hedgelord2.bsky.social did from it ☺️ #birds

0120

Reposted by Pierre Alquier

Francis Bach @bachfrancis.bsky.social · 04/10/2026

Frontier AI models are impacting us (researchers) in ways that we collectively need to make sense of. My colleague Pierre Marion has nicely put down his thoughts in writing in this insightful blog post. Enjoy! pierremarion23.github.io/thoughts/202...

0224

Pierre Alquier @pierrealquier.bsky.social · 05/10/2026

Black-crowned night heron at Jurong lake garden #birds

090

Pierre Alquier @pierrealquier.bsky.social · 04/10/2026

Parisian lovers enjoying their holidays in Singapore 😎 #birds

2163

Pierre Alquier @pierrealquier.bsky.social · 03/10/2026

Thomas Moellenhoff from RIKEN AIP (Tokyo) is visiting Singapore for a few days 😊

180

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 02/10/2026

USyd 🇦🇺 is hiring in CS! Tenure-track equivalent, junior/mid-career: usyd.wd105.myworkdayjobs.com/en-GB/USYD_E... With a focus on AI, but that includes TCS! Theory that helps building foundations of AI, gaining a deep understanding of it, or using AI in an ambitious way to solve deep problems...

usyd.wd105.myworkdayjobs.com

Multiple Continuing (Tenure-Track) Academic Positions, Faculty of Engineering, The University of Sydney

Join a thriving Faculty of Engineering at a University ranked amongst the world’s best teaching and research institutions and help shape the future of artificial intelligence and its impact across eve...

1146

Reposted by Pierre Alquier

Emily @emilydawn.bsky.social · 01/10/2026

@hockeyviz.com I found some beautiful data viz for you

7142321024

Pierre Alquier @pierrealquier.bsky.social · 02/10/2026

Coming back home late from work... It's dark already... It's good to see that Goisagi-san and Sasagoi-san are waiting for me anyway 🥲 Black-crowned night heron & little heron #birds

190

Pierre Alquier @pierrealquier.bsky.social · 02/10/2026

Here is something I needed someone to do, so that I can use it in my own reserach 😅 This looks very nice.

040

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 01/10/2026

"We want to encourage authors to be mindful with their work, taking care that they are submitting something substantial of scholarly interest that meets arXiv's guidelines and standards." 2 submissions per month, 3 active submissions blog.arxiv.org/2026/10/01/u... (per submitter, not listed author)

1273

Reposted by Pierre Alquier

arXiv @arxiv.bsky.social · 01/10/2026

arXiv has updated our policy on rate limiting for all submitters. This update was made to fairly distribute moderator time & support the arXiv community of staff, volunteers, readers & authors. Please read our announcement to learn more: blog.arxiv.org/2026/10/01/updated-r…

216773

Reposted by Pierre Alquier

Arthur Charpentier @freakonometrics.bsky.social · 01/10/2026

"ArXiv submission rates have steadily increased since our founding in 1991. In September, arXiv received 40,363 submissions in a single month – a new record." blog.arxiv.org/2026/10/01/u...

031

Reposted by Pierre Alquier

Christian Wolf @chriswolfvision.bsky.social · 01/10/2026

Je sens que Bluesky est pret pour des memes sur la causalité.

5235

Reposted by Pierre Alquier

Robin Ryder @robinryder.bsky.social · 01/10/2026

Many thanks to ISBA for taking a stand and for their support!

041

Reposted by Pierre Alquier

Robin Ryder @robinryder.bsky.social · 30/09/2026

Conference: Bayesian Methods for the Social Sciences III, Dublin, 9-11 December 2026. Join us! bayesforshs3.sciencesconf.org

bayesforshs3.sciencesconf.org

Bayesian Methods for the Social Sciences III - Sciencesconf.org

Sciencesconf.org

163

Reposted by Pierre Alquier

Sam Power @spmontecarlo.bsky.social · 30/09/2026

nice to see it framed so clearly

1454

Pierre Alquier @pierrealquier.bsky.social · 30/09/2026

The proceedings of ICML 2026 are online, including a position paper I took part to: proceedings.mlr.press/v306/papamar... The 29 other authors did all the work 😅 but I'm still proud to share it. Also I "officially" become a co-author of so many people I like a lot, this makes me sincerely happy 😊

proceedings.mlr.press

Position: Agentic AI Orchestration Should Be Bayes-Consistent

LLMs excel at predictive tasks and complex reasoning tasks, but many high-value deployments rely on decisions under uncertainty, for example, which tool to call, which expert to consult, or how man...

3101

Pierre Alquier @pierrealquier.bsky.social · 30/09/2026

Session on "Information Geometry and Variational Inference" at GDL 2026. Great talks by Marco Pacelli, Jérémie Houssineau, Thomas Möllenhoff and Frank Nielsen. I'm really intrigued by the "possibility theory" discussed by Jérémie in his talk...

2130

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 29/09/2026

If you're in #TheoreticalCS and on the postdoc job market, now or soon: this opportunity to work with Tom Gur (@tomgur.bsky.social) on "cutting-edge research on the interplay of theoretical computer science, mathematics, and quantum mechanics" sounds amazing: www.cam.ac.uk/jobs/researc...

cam.ac.uk

Research Assistant/Associate in Theoretical Computer Science (Fixed Term)

Fixed-term: The funds for this post are available for 1 year.

1226

Pierre Alquier @pierrealquier.bsky.social · 30/09/2026

Monk parakeet @ Kallang river. First time I get a photo of one of them. South-American bird, but there seem to be a small stable population of escapees in Singapore (far less common that the rose-ringed parakeet though) #birds

191

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 29/09/2026

The report from the AI + TCS Working Group held at the @simonsinstitute.bsky.social is out, including "twelve concrete near-term recommended actions." Currently reading it: while I have some reservations, but there is some good in it! Notably items 7, 8, and 11. simons.berkeley.edu/ai-tcs-worki...

7. Best works and technical talks in interviews.

- Emphasize quality over quantity. Evaluate candidates on no more than three works of their choosing, with this fact explicit in the instructions for candidates and their letter writers.

- Test technical depth. Evaluate the depth of the candidates’ understanding of the aforementioned works more than was done normally until now.

8. Additional postdocs. Establish additional postdoctoral positions for the TCS community, a temporary measure that will be phased out after a few years.

9. Workshops for identifying new theory directions. First, organize a workshop (or several) with the goal of identifying a list of modern topics related to AI; and second, run a series of workshops on each of these topics to identify fundamental directions and establish foundations and agendas for future work.

10. “TCS in the Age of AI” series at the Simons Institute. Establish a recurring and widely accessible “TCS in the Age of AI” series at the Simons Institute.

11. Opportunities for training and evaluation without AI assistance. To ensure development of necessary skills for a successful career in academia, a PhD in TCS should partially include training and evaluation components where the use of AI is forbidden.

43112

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 28/09/2026

By my wonderful colleague Katy Gero: A 4-month artist residency, Feb to May 2027, at the School of Computer Science at #USyd, "to support artists working on projects that involve serious consideration of computation and its related subjects." Share broadly, and apply! www.writefutureslab.com/air/

writefutureslab.com

Artist in Residence

2177

Reposted by Pierre Alquier

David Picard @davidpicard.eurosky.social · 28/09/2026

That's a great set of ideas, a must read for anyone starting. I think I would still do a PhD if I had to start today. I'm as excited to discover new stuff (and make cool new things) as I was when I started. Perhaps even more so now because of the complexity of what can be achieved.

0233

Pierre Alquier @pierrealquier.bsky.social · 29/09/2026

Little heron #birds (Formerly known as striated heron)

0282

Pierre Alquier @pierrealquier.bsky.social · 28/09/2026

One of the ugliest probability measures in the world 🤓 fr.wikipedia.org/wiki/Mesure_...

fr.wikipedia.org

Mesure de Dieudonné — Wikipédia

140

Pierre Alquier @pierrealquier.bsky.social · 28/09/2026

Attending the IAS Frontiers Conference on Geometry, Dynamics, and Learning (GDL 2026) at Nanyang Technological University. www.ntu.edu.sg/ias/news-eve...

070

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 28/09/2026

From our friends at the School of #Mathematics and Statistics at #USyd: positions as 'Magma Research Associates / Magma Research Fellows to develop and maintain the Magma computer #algebra system." 2 positions, each for 3 years: apply by October 20 usyd.wd105.myworkdayjobs.com/en-US/USYD_E...

usyd.wd105.myworkdayjobs.com

Magma Research Associate / Magma Research Fellow

2 x full time, 3-year fixed term positions, located on the Camperdown Campus at the School of Mathematics and Statistics Opportunity to drive research in computational pure mathematics through the dev...

189

Reposted by Pierre Alquier

Steven Seggie @stevenhseggie.bsky.social · 27/09/2026

The biggest evidence for success being driven by luck is listening to people like Thiel, Musk, Zuckerberg etc. Fish for brains.

1113

Reposted by Pierre Alquier

Thomas Dietterich @tdietterich.bsky.social · 27/09/2026

Excellent guest post analyzing the (somewhat sparse) data we have on recursive self improvement

1111

Pierre Alquier @pierrealquier.bsky.social · 28/09/2026

Grey heron @ Kallang river near Bishan park #birds

0332

Reposted by Pierre Alquier

Thomas Dietterich @tdietterich.bsky.social · 27/09/2026

Excellent essay by @philkoopman.bsky.social on how to regulate automated vehicle companies to be careful and competent. avsafety.substack.com/p/careful-an...

avsafety.substack.com

Careful & Competent Computer Drivers

Why aren’t we seeing data about reckless driving by AVs?

051

Reposted by Pierre Alquier

Clément Canonne @ccanonne.github.io · 27/09/2026

On the Theoretical CS job market? "The Algorithms and Complexity group of 🇫🇷 IRIF is seeking excellent candidates for postdoctoral positions in classical and quantum computing, with starting date in October 2027 (negotiable)." @irif-paris.bsky.social cstheory-jobs.org/2026/09/25/p...

1227

Pierre Alquier @pierrealquier.bsky.social · 27/09/2026

First time in Bishan park for quite a long time... I missed my heron friends 🥲 Purple heron #birds

1341

Pierre Alquier @pierrealquier.bsky.social · 26/09/2026

There's a new version of The Ring coming soon. This time I'm on TV and I'll crawl out, asking you to review papers written by AI

160

Reposted by Pierre Alquier

Francis Bach @bachfrancis.bsky.social · 25/09/2026

Overwhelmed by the variance of means of exponentials? This blog post is meant for you. As a bonus, a spectral closed-form formula for (approximate) multinomial logistic regression. francisbach.com/spectral_log...

0181

Reposted by Pierre Alquier

SHIMIZU Shohei @sshimizu2006.bsky.social · 24/09/2026

CLeaR 2027 welcomes submissions on causal learning and reasoning! Karthika and I are serving as Program Chairs, and we’d love to see your work. Submission deadline: November 16, 2026 (AoE) www.cclear.cc/2027

cclear.cc

CLeaR

031

Reposted by Pierre Alquier

Robin Ryder @robinryder.bsky.social · 24/09/2026

Join us! We are hiring Chapman Fellows in Statistics, within the Department of Mathematics at Imperial College London, commencing September 2027. We welcome applications across the breadth of Statistical Science. www.imperial.ac.uk/jobs/search-...

imperial.ac.uk

Description

Please note that job descriptions are not exhaustive, and you may be asked to take on additional duties that align with the key responsibilities ment...

173

Reposted by Pierre Alquier

Moritz Schauer @mschauer.bsky.social · 24/09/2026

#MathSky Trying to demystify Caratheodory's measure extension theorem: mschauer.github.io/share/friend...

mschauer.github.io

163

Reposted by Pierre Alquier

Anna Nagurney @annanagurney.bsky.social · 24/09/2026

Huge challenges faced by farmers in Ukraine www.kyivpost.com/post/85133. I'm proud of work done with @isenbergumass.bsky.social PhD student Dana Hassani + colleagues at the Kyiv School of Economics (KSE) and other universities in Ukraine thnx to the global partnership with @umassamherst.bsky.social

031

Reposted by Pierre Alquier

Michele Guindani @mguindani.bsky.social · 24/09/2026

There’s more here than meets the eye. AI shows both its potential and its limits: it can make us more productive, but is this the kind of productivity we want? Then again, perhaps Ramanujan would have left fewer results unproved, and Fermat would have needed less room in the margin…

151