Who's Who of AI

Pierre Alquier

199 trust researcher @pierrealquier.bsky.social · 3,411 followers
Professor of Statistics @ ESSEC Business School Asia-Pacific campus Singapore 🇸🇬 https://pierrealquier.github.io/ Previously: RIKEN AIP 🇯🇵 ENSAE Paris 🇫🇷 🇪🇺 UCD Dublin 🇮🇪 🇪🇺 Random posts about stats/maths/ML/AI, poor jokes & birds photo 🌈
What they're sharing

Articles & links

↻ Pierre Alquier reposted
Clément Canonne @ccanonne.github.io

A list of principles put forth by mathematicians, for mathematicians and other researchers, regarding the use of AI in research. "Number #9 will surprise you!" leidendeclaration.ai

Leiden Declaration on Artificial Intelligence and Mathematics leidendeclaration.ai
AI Weekly's analysis →
  • The Leiden Declaration, released June 2, 2026, warns AI threatens proof integrity, attribution, and peer review in mathematics.
  • Over 2,654 signatories including Fields Medal winner Terence Tao have endorsed the community-initiated declaration.
  • The International Mathematical Union backs the declaration, which makes separate recommendations to researchers, publishers, policymakers, and AI developers.
Read full analysis →
 View on Bluesky →
↻ Pierre Alquier reposted
Clément Canonne @ccanonne.github.io

New preprint up, led by Joy (Qiping) Yang and Yash Pote, with Jonathan Scarlett: we consider a relaxation of the standard (distribution) closeness testing task, where the algo now only needs to distinguish between p=q (equal) and |H(p)-H(q)|=Ω(1) (their entropies differ). 📝 ar…

[2605.23225] Entropy Equivalence Testing arxiv.org
AI Weekly's analysis →
  • Entropy equivalence testing needs significantly fewer samples than standard closeness testing for distributions.
  • The paper delivers the first non-trivial closeness testing algorithm for low-degree Bayesian networks.
  • Matching lower bounds establish near-optimality, revealing how hard the relaxed problem is in principle.
Read full analysis →
 View on Bluesky →
↻ Pierre Alquier reposted
Maxim Raginsky @mraginsky.bsky.social

Yifeng Chu and I just posted our paper on chaining-type bounds for expected soft maxima of Gaussian processes. The analysis makes use of a nice blend of ideas from probability, statistical physics of disordered systems, and information theory. arxiv.org/abs/2606.22611

Upper and Lower Bounds on Expected Soft Maxima of Gaussian Processes arxiv.org
AI Weekly's analysis →
  • The paper derives upper and lower bounds for soft maxima of centered Gaussian processes, defined as Gibbs averages at inverse temperature β > 0.
  • The bounds retain the same multiscale structure as generic chaining expressions, with a truncation term governed by the inverse temperature β.
  • As β → ∞, the bounds recover the majorizing measure theorem; applied to the Sherrington-Kirkpatrick model, they yield a finite-size Parisi formula.
Read full analysis →
 View on Bluesky →

Mehdi defends our recent preprint on rho-posteriors and their variational approximations at ISBA @Nagoya Link to the preprint: arxiv.org/abs/2601.07325

Robust Bayesian Inference via Variational Approximations of Generalized Rho-Posteriors arxiv.org
AI Weekly's analysis →
  • Khribch and Alquier introduce a rho-tilde-posterior that swaps the supremum over competitor parameters for a softmax aggregation.
  • The construction yields PAC-Bayesian finite-sample oracle inequalities with explicit convergence rates that survive model misspecification and data contamination.
  • Those guarantees extend to variational approximations, with computational cost the authors report as comparable to standard variational Bayes.
Read full analysis →
View on Bluesky · ♥ 9 ↻ 1 ↩ 0 · 2 from the directory shared this · 9d ago
↻ Pierre Alquier reposted
@csai-bot.bsky.social

Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov, Artem Vazhentsev, Preslav Nakov, Timothy Baldwin, Artem Shelmanov: Bayesian control for coding agents https://arxiv.org/abs/2606.24453 https://arxiv.org/pdf/2606.24453 https://arxiv.org/html/2606.24453

Bayesian control for coding agents arxiv.org
AI Weekly's analysis →
  • A new arxiv paper recasts coding-agent orchestration as cost-sensitive sequential hypothesis testing managed by a Bayesian controller.
  • The controller decides dynamically whether to gather more evidence, refine the solution, run a verifier, or stop the run.
  • Authors report the approach is most valuable when verification is costly and critics are informative but imperfect, across six generators and nine benchmarks.
Read full analysis →
 View on Bluesky →
↻ Pierre Alquier reposted
@csai-bot.bsky.social

Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov, Artem Vazhentsev, Preslav Nakov, Timothy Baldwin, Artem Shelmanov: Bayesian control for coding agents https://arxiv.org/abs/2606.24453 https://arxiv.org/pdf/2606.24453 https://arxiv.org/html/2606.24453

arxiv.org View on Bluesky →
↻ Pierre Alquier reposted
@csai-bot.bsky.social

Theodore Papamarkou, Vladislav Smirnov, Viktor Mazanov, Artem Vazhentsev, Preslav Nakov, Timothy Baldwin, Artem Shelmanov: Bayesian control for coding agents https://arxiv.org/abs/2606.24453 https://arxiv.org/pdf/2606.24453 https://arxiv.org/html/2606.24453

Bayesian Control for Coding Agents arxiv.org View on Bluesky →
↻ Pierre Alquier reposted
Maxim Raginsky @mraginsky.bsky.social

Video of the talk I gave at the Cultural AI conference at NYU back in March is finally up (thanks again to @leifw.bsky.social and @t-shoemaker.bsky.social for having arranged this excellent event). www.youtube.com/watch?v=iYu9...

youtube.com View on Bluesky →
↻ Pierre Alquier reposted
@probml.bsky.social

Excited that our ProbML symposium has now started (and is online on zoom: link is on probml.cc/schedule )! We have a full day of talks and posters on probabilistic machine learning.

Attending probml.cc View on Bluesky →
Their own posts

Recent commentary

We had a beautiful session on Markov chains in machine learning at the IMS Pacific Rim Meeting! Talks by Geoffrey Wolfer (Tokyo University of Agriculture and Technology), Vahe Karagulyan (ESSEC) and Daniel Paulin (NTU Singapore).

View on Bluesky · ♥ 8 ↻ 0 ↩ 1 · 25d ago

The session on Bayesian Deep Learning opens with a talk by Thomas Moellenhoff from RIKEN AIP 😊

View on Bluesky · ♥ 4 ↻ 0 ↩ 0 · 9d ago

Imon Banerjee stayed a few days at ESSEC to chat about Markov chains and machine learning. It was nice to have him here! 😊

View on Bluesky · ♥ 2 ↻ 0 ↩ 0 · 13d ago
Their network

In Pierre Alquier's orbit

Center = Pierre Alquier. Left = members they follow (green edges). Right = members who follow them (blue edges). Top = mutual follows (orange edges, slightly larger). Drag any node to reposition; click to open that profile.