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

Estimation with Quantized Parameter Side-Information

  • Mathis Wetterwald
  • Ofer Shayevitz
  • Michèle Wigger
Open at sourcePDFDOICite

Abstract

This paper presents upper and lower bounds on the minimax risk of a parameter estimation problem where the estimator not only observes independent and identically distributed observations but also a quantized version of the parameter, where the quantization has a limitation on the number of levels, but can be optimized otherwise. Our upper and lower bounds have similar decay rates for large number of observation samples and quantization levels.

Versions

Related

  1. Sharp parameter gaps for quantized Mabuchi energies and cscK metrics
    Kefeng Liu, Liangdi Zhang
    arXivPreprintCC BY-NC-ND 4.0Full textGeometry & topologyarXiv
  2. Four-Level Quantized Soft Information Aided Hard-Decision Decoder for Product-like Codes
    Xiaowei Wu, Min Qiu, Yueying Zhan +1
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  3. Minimum Rate For Partially Observable Linear System with Side Information: LQG Plant and Gaussian-Markov Source
    Sijie Li, Hyeji Kim
    arXivPreprintarXiv licenceFull textGeneral mathematicsarXiv
  4. Universal Distributed Feature Extraction Complementary to Side Information via H-Score
    Yuan Xinjie, Dier Tang, Shao-Lun Huang
    arXivPreprintCC BY 4.0Full textGeneral mathematicsarXiv
  5. Query-Dependent Reading for Quantized Inner-Product Estimation: A Minimax Separation
    Krishnakumar Balasubramanian, Siddharth Bhandari, Shiva Prasad Kasiviswanathan
    arXivPreprintCC BY 4.0Full textGeneral mathematicsarXiv

Cite

BibTeXRIS
BibTeX
@misc{wetterwald2026estimation,
  title = {{Estimation with Quantized Parameter Side-Information}},
  author = {Mathis Wetterwald and Ofer Shayevitz and Michèle Wigger},
  howpublished = {arXiv},
  year = {2026},
  month = oct,
  doi = {10.48550/arxiv.2610.11960},
  eprint = {2610.11960},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2610.11960},
  note = {CC BY 4.0},
}
RIS
TY  - UNPB
TI  - Estimation with Quantized Parameter Side-Information
AU  - Mathis Wetterwald
AU  - Ofer Shayevitz
AU  - Michèle Wigger
PY  - 2026
DA  - 2026/10/08
PB  - arXiv
DO  - 10.48550/arxiv.2610.11960
UR  - https://arxiv.org/abs/2610.11960
AB  - This paper presents upper and lower bounds on the minimax risk of a parameter estimation problem where the estimator not only observes independent and identically distributed observations but also a quantized version of the parameter, where the quantization has a limitation on the number of levels, but can be optimized otherwise. Our upper and lower bounds have similar decay rates for large number of observation samples and quantization levels.
ER  -