arbiter
JournalsPricingAccount

Decentralised convex optimisation with probability-proportional-to-size quantization

Dmitry Pasechnyuk et al.

EURO Journal on Computational Optimization2025https://doi.org/10.1016/j.ejco.2025.100113article
AJG 2
Weight
0.50

What the paper says

Communication is one of the bottlenecks of distributed optimisation and learning. To overcome this bottleneck, we propose a novel quantization method that transforms a vector into a sample of components' indices drawn from a categorical distribution with probabilities proportional to values at those components. Then, we propose a primal and a primal-dual accelerated stochastic gradient methods that use our proposed quantization, and derive their convergence rates in terms of probabilities of large deviations. We focus on affine-constrained convex optimisation and its application to decentralised distributed optimisation problems. To illustrate the work of our algorithm, we apply it to the decentralised computation of semi-discrete entropy regularized Wasserstein barycentre's.

Open paper page →

Cite this paper

https://doi.org/https://doi.org/10.1016/j.ejco.2025.100113

Or copy a formatted citation

@article{dmitry2025,
  title        = {{Decentralised convex optimisation with probability-proportional-to-size quantization}},
  author       = {Dmitry Pasechnyuk et al.},
  journal      = {EURO Journal on Computational Optimization},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.1016/j.ejco.2025.100113},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Decentralised convex optimisation with probability-proportional-to-size quantization

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.