ML Theory type of Person 🥳 Prof. for Statistical Learning @tuBraunschweig Shut the door quietly, please! @moskitos_bite@mastodon.social
Joined May 2021
- Tweets2.1K
- Following1.1K
- Followers1K
- Likes4.1K
Pinned Tweet
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.
Nic Mücke 🦩 🇪🇺 retweeted
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.
Nic Mücke 🦩 🇪🇺 retweeted
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.
Nic Mücke 🦩 🇪🇺 retweeted
Link: arxiv.org/abs/2505.14214
Nic Mücke 🦩 🇪🇺 retweeted
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
New preprint!
"Regularized least squares learning with heavy-tailed noise is minimax optimal"
joint work with @moskitos_bite, @DimitriMeunier1 and @ArthurGretton
Link: oeaw-ac-at.zoom.us/j/6291264…
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)
📢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)
I wish all the codes of conduct for research integrity that our scientific community has established would be rigorously enforced.
Are there any good mathy resources (intros or tutorials) about optimal transport, with applications in ML?
Nic Mücke 🦩 🇪🇺 retweeted
With another semester ending, here's your annual reminder that teaching evaluations systemically disadvantage women. Even when controlling for grades and other factors, students (esp. males) consistently give female professors lower scores. This can have serious ramifications.🧵
I have strong concerns about mathematical organizations that charge money for membership in a group focused on equity, diversity, and inclusion.
Nic Mücke 🦩 🇪🇺 retweeted
Do you know of a monograph PhD thesis written on the subject of Explainable AI (xAI)?
Re-tweets appreciated.
Nic Mücke 🦩 🇪🇺 retweeted
📣The Blog Post Track 2024 is out!
22 Blog posts on ML topics ranging from optimisation to RLHF:
blog.iclr.cc/2024/04/02/blog…
Tell your colleagues and friends!
@iclr_conf
@gauthier_gidel @busycalibrating @velythyl @fpedregosa Léo Schwinn
Nic Mücke 🦩 🇪🇺 retweeted
this is how statisticians computed linear regressions prior to the invention of the computer:
📢Our paper just got out:
For early stopped GD we derive minimax
rates of convergence. On our way, we precisely keep track of the number of hidden neurons required for generalization and improve over existing results.
sciencedirect.com/science/ar…
