Nic Mücke 🦩 🇪🇺

Check out our new result on regression with heavy-tailed noise ! Thanks to @gaussianmeasure , @DimitriMeunier1 , @ArthurGretton arxiv.org/abs/2505.14214

My issue with #NeurIPS2025: if a co-author fails to submit their assigned reviews, jointly submitted papers are not receiving reviews. Collective punishment is unfair and harmful, discouraging collaboration, penalizing innocent researchers, worsening the academic culture.

@miniapeur @gaussianmeasure @DimitriMeunier1 @ArthurGretton Hey! Thanks!

@moskitos_bite @gaussianmeasure @DimitriMeunier1 @ArthurGretton Hey nice to see you active again.

Check out our new result on regression with heavy-tailed noise ! Thanks to @gaussianmeasure , @DimitriMeunier1 , @ArthurGretton arxiv.org/abs/2505.14214

We introduce a Hilbert space version of the Fuk-Nagaev bound to the integral operator framework and generalize the typical “Bernstein-trick”: we use the capacity of the hypothesis space as a proxy for the higher moments, giving optimal rates.

We show that the optimal rates from the work by Caponnetto & De Vito (2007) hold without the assumption of sub exponential noise - you only need some finite higher moment.

Link: arxiv.org/abs/2505.14214

Check out our new result on regression with heavy-tailed noise ! I learned a lot on this project, thanks to @gaussianmeasure for leading the project. @moskitos_bite @ArthurGretton

@ilyamiskov The DVD contains video impressions from various washing machines. As a bonus, there are also recordings from a dryer.

Reply with some garbage products. I’ll start.

@RenateKuenast Those who interpret 'DEI' as preferential treatment for certain groups misunderstand its true meaning and origins.

Das nimmt langsam irre Formen an. „Mark Zuckerberg wants more 'masculine energy' and less diversity policy“ lemonde.fr/en/economy/art…

@miniapeur Do you want to tell us that you're not young anymore ...... ? 😲

My mom loooves to tell everyone that I was picky when I was young (which is true). Yet she's the one who doesn't want to try tacos or sushi 😢

@ProbFact In no other branch of mathematics do experts roll the dice on being wrong quite like in probability theory.

“In no other branch of mathematics is it so easy for experts to blunder as in probability theory.” — Martin Gardner

@Dirque_L Mich irritiert auch, dass bei einer W3 Professur immer noch von *früher Karrierephase* gesprochen wird ...

"Aufgrund der Ausstattung ist die Professur besonders für Wissenschaftler*innen in der frühen Karrierephase geeignet, die in Mannheim ein exzellentes Umfeld zur Weiterentwicklung finden." heißt doch nichts anderes als "Geld gibt's leider kaum…", oder? uni-mannheim.de/media/Universi…

@james_nichols @sp_monte_carlo depends on scientific maturity ... and will change accordingly

@miniapeur The moment when you reach the students, when you see in their faces that they have understood something bigger, is incredibly fulfilling.

@miniapeur We see the number of AI papers, not all of which need to be written, but have to be due to the pressure we are under in academia. Often, I find teaching more rewarding.

Today, I've met my cousin. He is around the same age as me, but he has a wife and two babies. It makes you realise that there's more to life than research and academia.

I challenge you to give a definition of "pure mathematics" that is 1) not using negation/exclusion and 2) not just a definition of "mathematics".

Organizers Werner Zellinger (RICAM), Nicole Mücke (TU Braunschweig), Luca Ratti (Uni Bologna), Tatiana Bubba (Uni Bath), Matteo Santacesaria (Uni Genoa), Sergei Pereverzyev (RICAM), Markus Holzleitner (Uni Genoa), Abhishake Rastogi (Uni LUT)

Link: oeaw-ac-at.zoom.us/j/62912641909?… Meeting-ID: 629 1264 1909 Kenncode: mZc4Zu

📢Next speaker in our online seminar about inverse problems and learning theory is Dirk Lorenz @Dirque_L with ** Learning regularizers - bilevel optimization or unrolling? ** When: June 18, 14:00–15:00 (CET)