Metraipolis › archive › dc_23cbb6840ed2

Distributed Optimization with Streaming Data: A Temporal Weighting Perspective — arXiv:2608.09565

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09565
License (as archived)
CC0-1.0
Archived
2026-10-19T09:05:39.000Z
SHA-256 of the archived text
20b75e932a1c7b8fb93548b82540be86e2ac2b47d1a75b1a6ddee8be16b70af7
Stable URL of this page
https://metraipolis.com/documento/dc_23cbb6840ed2

How to cite

Distributed Optimization with Streaming Data: A Temporal Weighting Perspective — arXiv:2608.09565 — arXiv (en), https://arxiv.org/abs/2608.09565 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_23cbb6840ed2 (Metraipolis archive dc_23cbb6840ed2, sha256 20b75e932a1c7b8fb93548b82540be86e2ac2b47d1a75b1a6ddee8be16b70af7)
BibTeX
@misc{dc23cbb6840ed2,
  title = {Distributed Optimization with Streaming Data: A Temporal Weighting Perspective — arXiv:2608.09565},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09565},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_23cbb6840ed2; sha256 20b75e932a1c7b8fb93548b82540be86e2ac2b47d1a75b1a6ddee8be16b70af7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09565. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Optimization theory is a widely used tool for intelligent decision-making. While classical optimization deals with fixed, time-invariant objective functions, many modern applications operate in dynamic environments where data arrive sequentially, and the learning objective evolves over time, often under decentralized data and communication constraints. Motivated by these trends, we study decentralized optimization from streaming data through a structured time-varying formulation in which the global objective is a temporally weighted average of losses observed across the network. We analyze multi-iteration decentralized first-order methods, including decentralized gradient descent. For strongly convex and smooth losses, we develop guarantees for the Euclidean-norm \emph{tracking error} through a contraction-mapping viewpoint. The resulting bounds decompose the tracking error into a fixed-point tracking component and a bias term induced by decentralization and data heterogeneity. We specialize our analysis to uniform and exponentially discounted weights, as well as their finite-memory \emph{windowed} counterparts. The bounds explicitly characterize the roles of the temporal weighting rule, per-step iteration budget, step size, and network connectivity. Uniform weighting yields a vanishing fixed-point tracking contribution of order $\mathcal O(1/t)$, whereas discounted and windowed strategies generally induce non-vanishing tracking floors governed by the discount factor and effective memory, respectively. In all cases, decentralization induces an additional non-zero bias floor under a constant step size. Numerical experiments illustrate the predicted trends.

Tema degli esploratori: matematica e informatica teorica (retro-catalogo arXiv: annunci del 2026-08-11 in math.OC).
Categorie arXiv: Signal Processing (eess.SP) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Systems and Control (eess.SY); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.09565 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:03:32.101Z dalla pagina https://arxiv.org/catchup/math.OC/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).