Metraipolis › archive › dc_5f27c6cbfa69

DICOMPUTE: An Economic and Privacy-Aware Framework for Distributed Artificial Intelligence Inference — arXiv:2611.10804

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.10804
License (as archived)
CC0-1.0
Archived
2026-11-10T18:45:42.589Z
SHA-256 of the archived text
7392be090c88c0688294d96cb8839da0d32acec021204e6a2036ddb64ea30ea2
Stable URL of this page
https://metraipolis.com/documento/dc_5f27c6cbfa69

How to cite

DICOMPUTE: An Economic and Privacy-Aware Framework for Distributed Artificial Intelligence Inference — arXiv:2611.10804 — arXiv (en), https://arxiv.org/abs/2611.10804 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5f27c6cbfa69 (Metraipolis archive dc_5f27c6cbfa69, sha256 7392be090c88c0688294d96cb8839da0d32acec021204e6a2036ddb64ea30ea2)
BibTeX
@misc{dc5f27c6cbfa69,
  title = {DICOMPUTE: An Economic and Privacy-Aware Framework for Distributed Artificial Intelligence Inference — arXiv:2611.10804},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.10804},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5f27c6cbfa69; sha256 7392be090c88c0688294d96cb8839da0d32acec021204e6a2036ddb64ea30ea2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.10804. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The prevailing design of large-scale artificial intelligence inference concentrates accelerators, model weights, and request processing in centralized computing facilities. Centralization offers important benefits in accelerator utilization, high-bandwidth interconnects, operational control, and serving efficiency. Yet centralized infrastructure is not always the least-cost or most governance-compatible choice for every inference workload. This paper develops a research framework for DICOMPUTE, a heterogeneous distributed inference architecture in which policy-constrained scheduling can allocate suitable requests across privately controlled, regional, and independently operated computing resources. We derive a full-cost comparison that accounts for capital amortization, energy, network transfer, orchestration, utilization, failures, and trust-related expenses; characterize conditions under which distributed inference can outperform centralized alternatives; and specify a privacy model separating data residency, transport confidentiality, execution confidentiality, and verifiable accounting. We propose falsifiable hypotheses and a reproducible experimental design, without presenting simulated examples as measured performance. Our central conclusion is conditional: distributed inference is most promising for divisible, latency-tolerant or locality-sensitive workloads on underutilized compatible hardware, while centralized clusters retain structural advantages for tightly coupled, memory-intensive, high-throughput inference. The framework is intended to support rigorous evaluation rather than to assert universal superiority.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.DC, nuovi lavori del giorno).
Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC).
Pagina del lavoro: https://arxiv.org/abs/2611.10804 — 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 2026-11-10T18:38:07.440Z dalla pagina https://arxiv.org/list/cs.DC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).