Skip to content
DraconiticResearch
Search Sources API
197,768 studies31 sourcesUpdated 12 min ago
PreprintCC BY 4.0arXiv

Risk-Averse Decision Making with Multi-Level Reliability Guarantees

  • Amirmohammad Farzaneh
  • Osvaldo Simeone
Open at sourcePDFDOICite

Abstract

Many applications in engineering, including wireless broadcasting, require designs that provide performance certificates at different target outage levels. This paper studies the problem of maximizing the weighted average of such certificates in the presence of uncertainty about the true system state. The problem is shown to be equivalent to an optimization over nested prediction sets, connecting to the literature on conformal prediction and extending prior art on single-level risk-averse decision making. Furthermore, we derive a dual formulation that decouples optimization across input values. Numerical experiments on a diversity-based wireless transmission system illustrate the cost of enforcing multi-level certificates with a single shared policy and trace the Pareto trade-off between multiple reliability levels.

Related

  1. Conformal Risk-Averse Decision Making with Optimized Certainty Equivalent Risk Control
    Amirmohammad Farzaneh, Osvaldo Simeone
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  2. Risk-Averse Decision Making via Quantum Measurement Design
    Meiyi Zhu, Osvaldo Simeone
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  3. Credal Machine Learning for Risk-Averse Decision Making
    Timo Löhr, Paul Hofman, Maximilian Muschalik +1
    arXivPreprintCC BY 4.0Full textStatisticsarXiv
  4. Risk Measures in Reliability Engineering: Comparison, Duality and Decision-Making
    Marie Temple-Boyer, Emma Cussenot, Guillaume Perrin +4
    HALPreprintCC BY 4.0Full textStatisticsHAL
  5. Risk-Averse Inference-Time Diffusion Model Alignment with Finite-Sample Guarantees
    Yuchen Liang, Xian Yu
    arXivPreprintCC BY 4.0Full textOptimisation & controlStatisticsarXiv

Cite

BibTeXRIS
BibTeX
@misc{farzaneh2026riskaverse,
  title = {{Risk-Averse Decision Making with Multi-Level Reliability Guarantees}},
  author = {Amirmohammad Farzaneh and Osvaldo Simeone},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.11524},
  eprint = {2609.11524},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.11524},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Risk-Averse Decision Making with Multi-Level Reliability Guarantees
AU  - Amirmohammad Farzaneh
AU  - Osvaldo Simeone
PY  - 2026
DA  - 2026/09/10
PB  - arXiv
DO  - 10.48550/arxiv.2609.11524
UR  - https://arxiv.org/abs/2609.11524
AB  - Many applications in engineering, including wireless broadcasting, require designs that provide performance certificates at different target outage levels. This paper studies the problem of maximizing the weighted average of such certificates in the presence of uncertainty about the true system state. The problem is shown to be equivalent to an optimization over nested prediction sets, connecting to the literature on conformal prediction and extending prior art on single-level risk-averse decision making. Furthermore, we derive a dual formulation that decouples optimization across input values. Numerical experiments on a diversity-based wireless transmission system illustrate the cost of enforcing multi-level certificates with a single shared policy and trace the Pareto trade-off between multiple reliability levels.
ER  -