heterogeneous-stochastic-momentum-admm
CommunityAdaptive momentum ADMM for robust optimization
Data & Analytics#stochastic optimization#federated learning#distributed optimization#admm#adaptive step size#heterogeneous networks
Authorhiyenwong
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Decouples algorithm stability from global network parameters to enable robust convergence for distributed non-convex composite optimization over heterogeneous network topologies.
Core Features & Use Cases
- Node-adaptive step sizes that scale with local degree, removing the need for global topology knowledge.
- Momentum-enhanced stochastic updates (STORM) combined with ADMM for faster convergence on distributed systems.
- Works on arbitrary connected topologies in distributed machine learning, federated learning, and network optimization.
Quick Start
Run HSM-ADMM on a connected graph with local gradients and proximal updates to reach consensus.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: heterogeneous-stochastic-momentum-admm Download link: https://github.com/hiyenwong/ai_collection/archive/main.zip#heterogeneous-stochastic-momentum-admm Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.