ℕathan ℝousselot

@BachFrancis Perfect timing! Congratulations

A happy author discovering the first hard copies

We are thrilled to say that NeurIPS@Paris is back for a 4th edition on the 4th and 5th of December 2024 at @Sorbonne_Univ_. A great occasion to meet + discuss recent advances in ML in central Paris! More info: neuripsinparis.github.io/neurips2024par… Registration: forms.gle/Fc4nbeW6ubahYb…

Lundi 16 septembre, Luca Calatroni et Emmanuel Soubies @EmmanuelSoubies optimisent et relaxent parcimonieusement le GdR IASIS avec "L0-based minimization: from continuous relaxations and non-convex algorithms to global optimization" gdr-iasis.cnrs.fr/reunion/522/

Our work on Target Strength measurements with SeapiX MBES has been published in the ICES Journal of Marine Science! @ICES_ASC @OxfordJournals @OUPAcademic – tinyurl.com/yk4jncpe

Mirror descent selects among the minimizers the one closest to initialization for the associated Bregman divergence (its "implicit bias"). Euclidean descent computes an orthogonal projection on the minimizers. arxiv.org/abs/1802.08246

📢 Offre de thèse ! Voir 👇. Please RT.

@FranckIutzeler @Univ_Toulouse @UT3PaulSabatier Welcome in Toulouse 😁

I'm glad to announce that I will join @Univ_Toulouse as a professor this fall. More precisely, I was promoted to PU at @UT3PaulSabatier and will be affiliated to the mathematics institute (IMT). Can't wait to start new collaborations in Toulouse!

Edouard Pauwels (IRIT): On the nature of Bregman functions arxiv.org/abs/2302.02689 arxiv.org/pdf/2302.02689

@ccanonne_ The algorithm cannot go wrong, I'd take any puns of yours. Crappy or high-quality, they never fail to make my day!

@gabrielpeyre If I'm not mistaken, the Choï-Williams distribution is fixing this interference issue. Though I am not sure about its downsides ? Worse precision due to the Gaussian component maybe, but I am guessing a bit haha. Wigner-Ville and all the other time-freq distributions are lovely!

The Wigner-Ville distribution mimics a probability distribution on the space-frequency plane. Useful to define the instantaneous frequency of a signal as the conditional expectation of frequencies. Suffers from interferences. en.wikipedia.org/wiki/Wigner_di…

Inria Grenoble is recruiting 5 junior researchers this year. Do not hesitate to apply ! The deadline is March 5th. A good practice is to first identify research teams that fits your profile and contact them inria.fr/en/inria-centr…

@TivadarDanka Even more beautiful: I think that means that exp(A) acts as a Graph Centralizer! Thus can be used to highlight the strongest links within a very large graph (traffic map e.g?). Since exp(A) = I + A + A²/2! + A³/3!

The single most undervalued fact of linear algebra: matrices are graphs, and graphs are matrices. Encoding matrices as graphs is a cheat code, making complex behavior simple to study. Let me show you how!

Have you been awaiting a mathematically rigorous theory of large neural networks? Then join me and @TheGregYang on his incredible Tensor Programs work, which both realizes such a theory and provides concrete experimental guidance to machine learning (1/n): youtu.be/1aXOXHA7Jcw

@lab_dai @kveeramac Happy holidays to you all!

#SeasonsGreetings from @kveeramac and the team at the #MIT Data-to-AI Lab #AIforGood

@cesifoti Foundation is a hit for me

What series do you recommend for the break? 📺 🎥 Recently I’ve enjoyed: Severance Ramy Stranger things The Morning Show The B* in Apt 23 The Mick The Detour Episodes Bless this mess Ted Lasso Brockmire Mo Californication Gringolandia Arcane The Good Place Brooklyn 99

CALL FOR PAPERS: IEEE Signal Processing Magazine welcomes submissions for a Special Issue on Hypercomplex Signal and Image Processing! Deadline to submit is 1 March 2023. Head to our website for details: signalprocessingsociety.org/blog/ieee-spm-…

📢 hiring research fellows at @cis_unimelb @engunimelb @UniMelb 🇦🇺 to work in any of ML, security, HCI w @vkostakos @tobycmurray Olya Ohrimenko, or me on @catch_muri. PhD preferred but flexible. Open to full- or part-time. Due Jan 19: go.unimelb.edu.au/p73e