Tootfinder

Ob du’s glaubst oder nicht: Das Eichhörnchen hat dich längst analysiert. 😍
#DietmarSchneider #Fotogalerie #Foto

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
Abdurakhmon Sadiev, Peter Richt\'arik, Ilyas Fatkhullin
https://arxiv.org/abs/2510.10690

Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits
Heavy-tailed noise is pervasive in modern machine learning applications, arising from data heterogeneity, outliers, and non-stationary stochastic environments. While second-order methods can significantly accelerate convergence in light-tailed or bounded-noise settings, such algorithms are often brittle and lack guarantees under heavy-tailed noise -- precisely the regimes where robustness is most critical. In this work, we take a first step toward a theoretical understanding of second-order opt…

Fiducial-Cosmology-dependent systematics for the DESI 2024 Full-Shape Analysis
R. Gsponer, S. Ramirez-Solano, F. Rodr\'iguez-Mart\'inez, M. Vargas-Maga\~na, S. Novell-Masot, N. Findlay, H. Gil-Mar\'in, P. Zarrouk, S. Nadathur, A. Rocher, S. Brieden, A. P\'erez-Fern\'andez, J. Aguilar, S. Ahlen, D. Bianchi, D. Brooks, F. J. Castander, T. Claybaugh, A. Cuceu, A. de la Macorra, A. de Mattia, Arjun Dey, P. Doel, A. Font-Ribera, J. E. Forero-Romero, E. Gazta\~naga, S. Go…

Fiducial-Cosmology-dependent systematics for the DESI 2024 Full-Shape Analysis
We assess the impact of the fiducial cosmology choice on cosmological inference from full-shape (FS) fits of the galaxy power spectrum in the DESI 2024 Data Release 1 (DR1). Using a suite of AbacusSummit DR1 mock catalogues based on the Planck 2018 best-fit cosmology, we quantify potential systematic shifts introduced by analysing the data under five secondary cosmologies - featuring variations in matter density, thawing dark energy, higher effective number of neutrino species, reduced clusteri…

Luise Königin von Preußen als Südseeschönheit 🌺🙂
Die Büste von Luise im Schlosspark Charlottenburg ist jeden Tag anders gestylt – und das schon seit Jahren!
Ich hatte bisher noch nicht das Glück, den/die Stylist:in zu treffen.
Luise Königin von Preußen (✶ 10. 03. 1776 – † 19. 07.1810)
#Fotogalerie

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Wanli Ni, Hui Tian, Shuai Wang, Chengyang Li, Lei Sun, Zhaohui Yang
https://arxiv.org/abs/2510.05713

Federated Split Learning for Resource-Constrained Robots in Industrial IoT: Framework Comparison, Optimization Strategies, and Future Directions
Federated split learning (FedSL) has emerged as a promising paradigm for enabling collaborative intelligence in industrial Internet of Things (IoT) systems, particularly in smart factories where data privacy, communication efficiency, and device heterogeneity are critical concerns. In this article, we present a comprehensive study of FedSL frameworks tailored for resource-constrained robots in industrial scenarios. We compare synchronous, asynchronous, hierarchical, and heterogeneous FedSL fram…

Global Solutions to Non-Convex Functional Constrained Problems with Hidden Convexity
Ilyas Fatkhullin, Niao He, Guanghui Lan, Florian Wolf
https://arxiv.org/abs/2511.10626 https://arxiv.org/pdf/2511.10626 https://arxiv.org/html/2511.10626
arXiv:2511.10626v1 Announce Type: new
Abstract: Constrained non-convex optimization is fundamentally challenging, as global solutions are generally intractable and constraint qualifications may not hold. However, in many applications, including safe policy optimization in control and reinforcement learning, such problems possess hidden convexity, meaning they can be reformulated as convex programs via a nonlinear invertible transformation. Typically such transformations are implicit or unknown, making the direct link with the convex program impossible. On the other hand, (sub-)gradients with respect to the original variables are often accessible or can be easily estimated, which motivates algorithms that operate directly in the original (non-convex) problem space using standard (sub-)gradient oracles. In this work, we develop the first algorithms to provably solve such non-convex problems to global minima. First, using a modified inexact proximal point method, we establish global last-iterate convergence guarantees with $\widetilde{\mathcal{O}}(\varepsilon^{-3})$ oracle complexity in non-smooth setting. For smooth problems, we propose a new bundle-level type method based on linearly constrained quadratic subproblems, improving the oracle complexity to $\widetilde{\mathcal{O}}(\varepsilon^{-1})$. Surprisingly, despite non-convexity, our methodology does not require any constraint qualifications, can handle hidden convex equality constraints, and achieves complexities matching those for solving unconstrained hidden convex optimization.
toXiv_bot_toot

Graureiher beim Snacken... 2/2
#DietmarSchneider #Fotogalerie #Foto #Photography

Graureiher beim Snacken... 1/2
#DietmarSchneider #Fotogalerie #Foto #Photography

Herrje wie süß! Eine aufgeplusterte Kohlmeise...❤️
#DietmarSchneider #Fotogalerie #Foto #Photography

So süß wie sich das Eichhörnchen mit einem Pfötchen abstützt 😍
#DietmarSchneider #Fotogalerie #Foto #Photography