Fun (...) fact: the only linear operators on matrices that preserves the rank are X->AXB, where A and B are invertible (with X->X^T in the square case). This was apparently first proved (?) in 1959 by Marcus and Moyls.

Kevin Tierney talks at the CRM workshop Combinatorial Optimization & Data Science about solving combinatorial optimization problems with deep reinforcement learning.

1/N

Characterizing finely the decay of eigenvalues of kernel matrices: many people need it, but explicit references are hard to find. This blog post reviews amazing asymptotic results from Harold Widom (1963!) and proposes new non-asymptotic bounds.
francisbach.com/spectrum-ker...

This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235

🚀 INRAE recrute 58 Chargés de recherche (F/H) ! 🌱
📢 Les concours sont ouverts du 28 janvier au 4 mars pour les chercheurs en début de carrière, titulaires d’un doctorat.

📅 Dates clés :
▶️ Avril : Pré-sélection s/ dossier
▶️ 2–18 juin : Entretien de sélection

🔗 Postulez dès maintenant : jobs.inrae.fr