A decentralized Sinkhorn algorithm approximates Wasserstein barycenters using local gossip protocols, event-triggered transmissions, and b-bit quantization, with proven convergence to a neighborhood of the centralized entropic solution under mild assumptions.
A dual approach for optimal algorithms in distributed opti- mization over networks.IEEE Transactions on Automatic Control, 63(10):3265–3280
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SY 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometry-Aware Decentralized Sinkhorn for Wasserstein Barycenters
A decentralized Sinkhorn algorithm approximates Wasserstein barycenters using local gossip protocols, event-triggered transmissions, and b-bit quantization, with proven convergence to a neighborhood of the centralized entropic solution under mild assumptions.