Metraipolis › archive › dc_addbc4b8bfb7

Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy — arXiv:2609.12067

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.12067
License (as archived)
CC0-1.0
Archived
2026-10-16T03:15:30.496Z
SHA-256 of the archived text
2cf31345a3f89372efbf931ba2c0aada30863265536689631151d664d4e3943e
Stable URL of this page
https://metraipolis.com/documento/dc_addbc4b8bfb7

How to cite

Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy — arXiv:2609.12067 — arXiv (en), https://arxiv.org/abs/2609.12067 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_addbc4b8bfb7 (Metraipolis archive dc_addbc4b8bfb7, sha256 2cf31345a3f89372efbf931ba2c0aada30863265536689631151d664d4e3943e)
BibTeX
@misc{dcaddbc4b8bfb7,
  title = {Scalable Discrete-to-Continuous Channel Simulation for Compression and Privacy — arXiv:2609.12067},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12067},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_addbc4b8bfb7; sha256 2cf31345a3f89372efbf931ba2c0aada30863265536689631151d664d4e3943e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12067. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Channel simulation has recently emerged as a useful component in machine learning systems where samples from a prescribed probability distribution are to be compressed. Yet, general channel simulation algorithms often suffer from high computational costs, random stopping times or, in the worst case, can require generating an infinite number of shared random samples. We introduce a scheme for both exact and approximate simulation of discrete-to-continuous channels which conversely uses a fixed number of random samples, and therefore has a runtime independent of the channel and the input. Unlike existing channel simulation schemes which generate a sequence of independent samples from a proposal distribution, our approach generates one sample, or alternatively a fixed number of samples, from each potential target distribution. We then apply a latent permutation to the samples before performing sample selection using an exponential race. Our scheme provides a flexible tradeoff between the number of generated samples and the compression rate. Using polar and multilevel coding, we scale our approach to handle long blocklengths in $O(n \log n)$ time in order to benefit from reduced per-symbol overhead. We conclude by demonstrating applications to variable-rate compression with stochastic VQ-VAEs and communication-efficient differentially private distributed mean estimation via exact simulation of the Gaussian mechanism.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Information Theory (cs.IT).
Pagina del lavoro: https://arxiv.org/abs/2609.12067 — 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 2026-10-16T03:05:44.012Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).