Tootfinder

Distributed Stochastic Optimization under Heavy-Tailed Noise: A Federated Mirror Descent Approach with High Probability Convergence
Zhan Yu, Lan Liao, Deming Yuan, Daniel W. C. Ho, Ding-Xuan Zhou
https://arxiv.org/abs/2509.17659

Distributed Stochastic Optimization under Heavy-Tailed Noise: A Federated Mirror Descent Approach with High Probability Convergence
We study the distributed stochastic optimization (DSO) problem under a heavy-tailed noise condition by utilizing a multi-agent system. Despite the extensive research on DSO algorithms used to solve DSO problems under light-tailed noise conditions (such as Gaussian noise), there is a significant lack of study of DSO algorithms in the context of heavy-tailed random noise. Classical DSO approaches in a heavy-tailed setting may present poor convergence behaviors. Therefore, developing DSO methods i…

Major kudos to the people who put together the tracks for this new compilation of power pop songs.
Some real hidden gems in here, like the early tracks from The Bongos and The Smithereens.
It covers the decade quite well with the early 80s stuff that's often included in these comps, through to the late 80s with deep cuts from Redd Kross and The Pursuit of Happiness.
#music

Various Artists: I Wanna Be A Teen Again - American Power Pop 1980-1989, 3CD Box Set
• 3CD CELEBRATION OF CLASSIC AND RARE NORTH AMERICAN POWER POP OF THE 1980s.• OVER 75 TRACKS FULL OF HOOKS, HARMONIES & HIGH ENERGY!• FEATURING THE FLAMIN' GROOVIES, CHEAP TRICK, THE GO-GOS, THE RAMONES, THE BANGLES, REDD KROSS, THE KNACK, THE ROMANTICS, STIV BATORS, THE SHIVVERS, THE SMITHEREENS, THE VELVET CRUSH, MATERIAL ISSUE, DWIGHT TWILLEY, PHIL SEYMOUR, ERIC CARMEN, NIKKI & THE CORVETTES, PAUL COLLINS' BEAT, 20/20, RICK SPRINGFIELD, SHOES, THE LONG RYDERS, UTOPIA AND SCORES MORE….

2025 #NewMexico Mineral Symposium for both professionals and amateurs interested in #mineralogy. Socorro, NM Nov 7 -9
Featured Speaker:
"History and Highlights, including New Mexico specimens, of the Natural History Museum, London, England"
-Mike Rumsey, Principal Curator of…

NM Mineral Symposium

Privacy-Preserving Multimodal News Recommendation through Federated Learning
Mehdi Khalaj, Shahrzad Golestani Najafabadi, Julita Vassileva
https://arxiv.org/abs/2507.15460

Privacy-Preserving Multimodal News Recommendation through Federated Learning
Personalized News Recommendation systems (PNR) have emerged as a solution to information overload by predicting and suggesting news items tailored to individual user interests. However, traditional PNR systems face several challenges, including an overreliance on textual content, common neglect of short-term user interests, and significant privacy concerns due to centralized data storage. This paper addresses these issues by introducing a novel multimodal federated learning-based approach for n…

Our paper was featured in a nice article of the Critical Zone Newsletter. Thank you very much @… 😀
https://criticalzonenews.substack.com/p/stone-gardens-after-ice-the-slow

Zurück am Arbeitsplatz möchte ich darum erst recht nicht unerwähnt lassen, dass ich die Blaufusstölpel vorher noch fertigbekommen habe und die zwei #wandklex Originale jetzt im Klexshop auf #blaufusstoelpel #fediArt #mastoArt #creativeToots

Sporadic Federated Learning Approach in Quantum Environment to Tackle Quantum Noise
Ratun Rahman, Atit Pokharel, Dinh C. Nguyen
https://arxiv.org/abs/2507.12492

Sporadic Federated Learning Approach in Quantum Environment to Tackle Quantum Noise
Quantum Federated Learning (QFL) is an emerging paradigm that combines quantum computing and federated learning (FL) to enable decentralized model training while maintaining data privacy over quantum networks. However, quantum noise remains a significant barrier in QFL, since modern quantum devices experience heterogeneous noise levels due to variances in hardware quality and sensitivity to quantum decoherence, resulting in inadequate training performance. To address this issue, we propose SpoQ…

Nice,
"Europe Launches Its First Federated AI Factory Based on a Sovereign Multi-Cloud Infrastructure"
#ai #cloud #eu

PeerTube is a decentralized alternative to YouTube
that doesn't believe in harvesting user data and pushing people into echo chambers via a proprietary algorithm.
Built on open standards and federation,
it lets communities host and share video without depending on a central server.
https://news.itsfoss.com/peertube-7…

Decentralized YouTube Alternative Adds Live Streame Scheduling Option in Latest Release
Also adds multilingual emails, improved admin tools, and session management.

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Nobin Sarwar, Shubhashis Roy Dipta
https://arxiv.org/abs/2509.14275 https://

FedMentor: Domain-Aware Differential Privacy for Heterogeneous Federated LLMs in Mental Health
Privacy-preserving adaptation of Large Language Models (LLMs) in sensitive domains (e.g., mental health) requires balancing strict confidentiality with model utility and safety. We propose FedMentor, a federated fine-tuning framework that integrates Low-Rank Adaptation (LoRA) and domain-aware Differential Privacy (DP) to meet per-domain privacy budgets while maintaining performance. Each client (domain) applies a custom DP noise scale proportional to its data sensitivity, and the server adaptiv…