Hugging Face Trending Papers
Group Distributionally Robust Optimization over Decentralized Networks
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Machine Learning
Oct 22
Group Distributionally Robust Optimization over Decentralized Networks
arXiv:2610. 29261v1 Announce Type: cross Abstract: We study group distributionally robust optimization (GDRO) over decentralized networks, where workers collaborate to learn robust models by minimizing the maximum local risk.
arXiv Machine Learning
Jun 4
Near-Optimal Decentralized Stochastic Convex Optimization over Networks
arXiv:2606. 04757v1 Announce Type: cross Abstract: We study decentralized stochastic smooth convex optimization, where $M$ workers minimize an average objective using local stochastic gradients and neighbor-only communication over a fixed gossip network.
arXiv Machine Learning
Oct 8
Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping
arXiv:2610. 10527v1 Announce Type: cross Abstract: Heavy-tailed noise has been widely observed in modern machine learning, motivating the use of methods like gradient clipping and normalization.
arXiv Machine Learning
Jun 8
Accelerated Decentralized Stochastic Gradient Descent for Strongly Convex Optimization
arXiv:2606. 07496v1 Announce Type: new Abstract: Decentralized stochastic optimization is a fundamental paradigm for large-scale learning over networks, where agents communicate only with their neighbors and no central coordinator is required.
arXiv AI
Sep 1
Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization
The paper introduces Dec-BFTRL, a decentralized algorithm for online optimization of upper-linearizable payoffs with efficient separation access, targeting continuous diminishing-return submodular maximization. Each agent evaluates its action against the average of local objectives, projects via an approximate gauge, exchanges a cumulative surrogate-gradient dual state, and uses a local HybridNewton step to minimize its BFTRL potential. The method achieves an expected network-aggregate regret of “~O(√T)” while requiring T neighbor-mixing steps and ~O(T) separation-oracle calls per agent, and provides four wrapper instantiations for three DR-submodular problems.
Hugging Face Trending Papers
Aug 31
Dec-BFTRL: Squre-Root Regret for Decentralized Online Upper-Linearizable Optimization under Separation Access with Application to Continuous Submodular Maximization
We study decentralized online optimization of upper-linearizable payoffs over an action set under efficient separation access, with applications to online continuous diminishing-return (DR) submodular...