Sofiane Tanji

Saving peer review from AI slop requires getting rid of anonymous submissions and reviews
togelius.blogspot.com/2026/03/savi...

📢 Plenary speakers for #ISMP2027

We are pleased to announce the plenaries for the 26th International Symposium on Mathematical Programming:

Daniel Bienstock
Jim Luedtke @optimizer.bsky.social
Thomas Rothvoss
Katya Scheinberg
Defeng Sun

🗓️ July 25–30, 2027

📍Amsterdam
🔗 ismp2027.mathopt.nl

#MOS

$k$-SVD with Gradient Descent The emergence of modern compute infrastructure for iterative optimization has led to great interest in developing optimization-based approaches for a scalable computation of $k$-SVD, i.e., the $k\geq ...

It’s even more surprising to me that it still shows up in recent research, eg this paper arxiv.org/abs/2502.00320 where the authors draw connections between herons method and GD applied to compute k-svd

That’s a neat way to see that Heron’s method converges quadratically (w_n being some kind of error measure).
It’s always surprising to me that fast converging schemes like this one were discovered so early

L'application saracroche.org/fr

I really wish #OpenAI would stop releasing free stochastic parrots in every community they can think of.
They sure look pretty but they are shitting all over the place and you can't have a decent conversation between humans anymore.

How can we get access to the client ?

**Please repost** If you're enjoying Paper Skygest -- our personalized feed of academic content on Bluesky -- we'd appreciate you reposting this! We’ve found that the most effective way for us to reach new users and communities is through users sharing it with their network

New paper out! Together with my postdoc advisors @esoubies.bsky.social and Cédric Févotte :)

We study the optimization landscape of L0-Bregman relaxations, which naturally arise when one optimizes non-quadratic fidelity terms coupled with the L0-norm.

1/n

Lately, I have been obsessed with developing theoretically based optimization algorithms that actually attain the best practical performance.
Alas, the classic model of minimax optimal methods is overly conservative; it overfits to tune its worst-case.
We found a path forward 1/

MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)

I have several offers for Master internships / PhDs on graph ML funded by ERC MALAGA for 2026. Don't hesitate to contact me to apply!

All infos here: nkeriven.github.io/malaga/

A regrettable sign of the times, but it shouldn’t be misreported: they aren’t restricting most CS papers. They are restricting ONLY review/survey papers and position papers, which weren’t common in CS anyway prior to the AI onslaught. No new restrictions on CS papers consisting of original research.

I’m recruiting a postdoctoral researcher on a fully funded 2-year contract. The topic is developing and implementing new parallel graph algorithms, with applications to data-driven transportation and logistics.
Details and application procedure below ⬇️ Reach out if you have any questions!

Yes informatique covers ~ academic CS, software, IT

Ingénieur informaticien / ingénieur en informatique / sciences informatiques are not awkward.
About 2: Informatique is the most idiomatic.
About why it’s prevalent, I don’t know. French just came up with a different word before the term « computer science » crossed the border.

We can combine the word for engineering and « informatique ». For example, ingénieur informatique = software engineer.
You may read sometimes « sciences informatiques » to distinguish CS as a science from CS as an industry.
Saying sciences d’informatique / de l’informatique is not idiomatic

An interesting knock-on effect of various recent hype cycles at the intersection of LLMs and Maths is that I've found some motivation to care a bit more about what people really mean by "open problem".

Fraisier also means the plant on which strawberries grow

How is the experience so far ?

#ICLR2026 PCs consider prompt injection as an ethics problem, in particular an attempt to collude with a potential malicious reviewer (using an LLM). I can't agree more.

blog.iclr.cc/2025/08/26/p...

My newish go-to "intro to RL from first principles" is Ch. 11/12 of Moritz Hardt & @beenwrekt.bsky.social's ML book. They're not 100% standalone chapters but can work that way. I now like this as an intro more than Sutton & Barto (more concise, conceptually clearer, connections w/ control theory).

Announcing : The 2nd International Summer School on Mathematical Aspects of Data Science
mathsdata2025.github.io
EPFL, Sept 1–5, 2025

Speakers:
Bach @bachfrancis.bsky.social
Bandeira
Mallat
Montanari
Peyré @gabrielpeyre.bsky.social

For PhD students & early-career researchers
Apply before May 15!

The problem with most machine-based random number generators is that they’re not TRULY random, so if you need genuine randomness it is sometimes necessary to link your code to an external random process like a physical noise source or the current rate of US tariffs on a given country.

Pour 1/, il y a un super article d’Alexander Ioffe à ce sujet, « an invitation to tame optimization »

1-day workshop on Bilevel optimization and hyperparameter tuning at ENS de Lyon, on March 25th : gdr-iasis.cnrs.fr/reunions/bil...

Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!

🎓🌞 Join the PhD course on Theoretical Foundations of Machine Learning at 🇮🇹 ELLIS Unit Genoa, June 23-27, 2025, hosted by Machine Learning Genoa Center.

🗓️ Apply by: March 16, 2025
📍 University of Genoa (in-person only)

💡 More info: malga.unige.it/education/sc...

The University of Pittsburgh pauses its Ph.D. admissions process amid research funding uncertainty A spokesperson for the University told WESA Friday that the school has "temporarily paused additional Ph.D. offers of admission," while Pitt works to understand how proposed federal funding cuts could...

The University of Pittsburgh confirmed Friday that there would be no new Ph.D. offers of admission while Pitt works to understand how reduced federal aid could impact the institution.

Yurii Nesterov: Optimization, the Philosophical Background of Artificial Intelligence #ICBS2024 YouTube video by BIMSA

Momentum I didn't read/hear but he used the expression "look ahead" a few times, see for example here: youtu.be/Z_ktoBqIdKg?... (discussion from 18mn to 23mn)

Happy to share our work on learning theory for kernel bilevel optimization! Grateful to Edouard, @samuelvaiter.com, and @michael-arbel.bsky.social for their mentorship and insightful discussions that shaped this paper!