Metraipolis › archive › dc_a887b403bc6e

Expected Minimax Regret Rates for Adaptive LQG Control on Fixed Parameter Sets — arXiv:2611.01739

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.01739
License (as archived)
CC0-1.0
Archived
2026-11-03T18:45:30.090Z
SHA-256 of the archived text
6637551fd83fea27ec8468aa9539aeef6382b7e319bfd0b27151bd63b32b16d7
Stable URL of this page
https://metraipolis.com/documento/dc_a887b403bc6e

How to cite

Expected Minimax Regret Rates for Adaptive LQG Control on Fixed Parameter Sets — arXiv:2611.01739 — arXiv (en), https://arxiv.org/abs/2611.01739 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a887b403bc6e (Metraipolis archive dc_a887b403bc6e, sha256 6637551fd83fea27ec8468aa9539aeef6382b7e319bfd0b27151bd63b32b16d7)
BibTeX
@misc{dca887b403bc6e,
  title = {Expected Minimax Regret Rates for Adaptive LQG Control on Fixed Parameter Sets — arXiv:2611.01739},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01739},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a887b403bc6e; sha256 6637551fd83fea27ec8468aa9539aeef6382b7e319bfd0b27151bd63b32b16d7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01739. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study how a fixed model family determines expected minimax regret in adaptive LQG control. The family is compact and affine, with partial observation and unknown noise covariances. We quantify how information from residual covariances and input responses can vanish relative to differences between optimal control laws. This relation yields matching bounds that classify regret as bounded, logarithmic, sublinear polynomial or linear. Polynomial exponents are rational. For real algebraic model and cost data, a terminating procedure determines the regret class and the exact exponent of polynomial growth before data collection. A causal policy attains these rates using model estimation and bounded probes, reselecting model sets from observations without a supplied common stabilizer. For costs with fixed positive definite output and input weights, polynomial exponents are at most one half.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2611.01739 — 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 2026-11-03T18:14:37.767Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).