Block Coordinate Descent

Latest papers

8 papers2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

ParaBlock++: Communication-Computation Parallel Blockwise Hierarchical Federated Learning
Oct 31, 2026Kai Wang, Chee Wei TanBlock Coordinate Descent Federated Learning
College of Computing and Data Science, Nanyang Technological University, Singapore 639798
Local Work, Global Progress: A Convergence Theory of AI Agent Collaboration
Oct 20, 2026Ivan Ilin, Peter RichtárikBlock Coordinate Descent Multi-Agent Collaboration
KAUST
Predicting Block-Coordinate Performance via Cross-Curvature
Sep 27, 2026Shengkun Zhu, Jinshan Zeng, Zhiqiang Kou +2Neural Network Optimization Block Coordinate Descent
The Hong Kong Polytechnic University · School of Management, Xi’an Jiaotong University · Beijing Key Laboratory of AI-Native Data Systems and SKLCCSE Lab, Beihang University
ABCD: Alpha-Composited Block Coordinate Descent: Constant-VRAM Training for Large Radiance Fields
Aug 27, 2026Ka Heng Shiu, Kartic SubrBlock Coordinate Descent Neural Rendering
The University of Edinburgh, Edinburgh, United Kingdom
DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data
Jun 2, 2026Yunsheng Yuan, Shaowei Li, Kai Wang +5Fine-Tuning LLM Fine-Tuning
School of Computer Science and Technology, Shandong University, Qingdao China · School of Mathematical Science, Peking University, China · IEIT SYSTEM, China +2
Turning Stale Gradients into Stable Gradients: Coherent Coordinate Descent with Implicit Landscape Smoothing for Lightweight Zeroth-Order Optimization
May 14, 2026Chen Liang, Xiatao Sun, Qian Wang +1Zeroth-Order Optimization Block Coordinate Descent
Department of Computer Science, Yale University, New Haven, USA.
FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
Mar 5, 2026Junkang Liu, Fanhua Shang, Yuanyuan Liu +3Block Coordinate Descent Federated Learning
School of Artificial Intelligence, Xi’an, Xidian University, China · College of Intelligence and Computing, Tianjin, Tianjin University, China · Medical College, Tianjin University; Peng Cheng Laboratory, Tianjin, China +1
Multi-Agent Temporal Logic Planning via Penalty Functions and Block-Coordinate Optimization
Feb 19, 2026Eleftherios E. Vlahakis, Arash Bahari Kordabad, Lars Lindemann +3STL Planning Block Coordinate Descent
the Division of Computer Engineering and Computer Science, University West, 46132, Trollhättan, Sweden · the Max Planck Institute for Software Systems, Kaiserslautern, Germany · the Automatic Control Laboratory, ETH Zürich, 8092, Zürich, Switzerland +2

Oct 31, 2026J/K move · Enter open · S save

ParaBlock++: Communication-Computation Parallel Blockwise Hierarchical Federated Learning

Kai Wang, Chee Wei Tan

College of Computing and Data Science, Nanyang Technological University, Singapore 639798

Block Coordinate Descent Federated Learning Hierarchical Federated Learning Communication-Efficient Distributed Training Asynchronous Federated Learning

Open paper AskPDF arXiv

In the emerging 6G paradigm, where AI-driven services operate over decentralized and resource-constrained infrastructures, the convergence of distributed learning algorithms remains a significant challenge. This paper introduces

\mathrm{ParaBlock}

++, a low Earth orbit (LEO) satellite-assisted hierarchical federated learning (HFL) framework, enabling resource-limited terrestrial clients to collaboratively engage in federated learning (FL) via ground-satellite links (GSLs) supported by LEO satellite megaconstellations. Within this architecture, LEO satellites serve multiple roles: as edge servers aggregating and broadcasting models, as clients accelerating training, and as high-throughput relays managing inter-satellite routing through inter-satellite links (ISLs). Departing from conventional synchronous Jacobian-type updates,

\mathrm{ParaBlock}

++ employs asynchronous BCD-type updates to enhance convergence speed. We provide theoretical convergence guarantees for convex, strongly convex, and non-convex objectives, and formulate optimization problems to determine optimal cluster resource allocation and model partitioning for minimizing global training latency. Experimental evaluations demonstrate that

\mathrm{ParaBlock}

++ achieves faster initial convergence and comparable final performance for deep neural networks (DNNs) such as ResNet-18, offering promising directions for federated learning across geographically remote areas enabled by 6G technologies, but much less global rounds and communication cost.