Metraipolis › archive › dc_4329f5e5cbdf
Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty — arXiv:2608.13651
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.13651
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:30:44.359Z
- SHA-256 of the archived text
bf0bda044123e7bb8f6b5329d162a73814f0efeca9597a7435ba9532ff353aed- Stable URL of this page
https://metraipolis.com/documento/dc_4329f5e5cbdf
How to cite
Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty — arXiv:2608.13651 — arXiv (en), https://arxiv.org/abs/2608.13651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4329f5e5cbdf (Metraipolis archive dc_4329f5e5cbdf, sha256 bf0bda044123e7bb8f6b5329d162a73814f0efeca9597a7435ba9532ff353aed)
BibTeX
@misc{dc4329f5e5cbdf,
title = {Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty — arXiv:2608.13651},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.13651},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4329f5e5cbdf; sha256 bf0bda044123e7bb8f6b5329d162a73814f0efeca9597a7435ba9532ff353aed},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We solve exactly a fundamental problem of adaptive control against adversarial disturbances: regulate the scalar system $x_{t+1} = ax_t + u_t + w_t$, $x_0=0$, $\|w\|_\infty \le 1$, where the constant pole $a \in [-\Delta, \Delta]$ is unknown in sign and magnitude and $\Delta$ is arbitrarily large. Elementary as the system looks, the least worst-case peak $\|x\|_\infty$ that a causal controller can guarantee against an adversarial pair $(a, w)$ (the value of this game) has, to our knowledge, never been determined for any adaptive control problem with parametric uncertainty of arbitrary size under this criterion; existing theory supplies stability certificates, gain bounds, and regret rates, not the value. That value is $\gamma^\star(\Delta) = 1 + \Delta$ for every $\Delta>0$. The summand $1$ is the irreducible price of the disturbance, and $\Delta$ the exact price of a single, unavoidable identification spike. The optimal policy is certainty-equivalent deadbeat control at the midpoint of the set-membership consistent interval, an instance of the robust oracle $\times$ consistent model chasing architecture. The architecture is forced, not merely sufficient: writing $\theta_t := -u_t/x_t$ exhibits every causal controller as an oracle-selector composition, and optimality pins the selector to the midpoint at the critical histories. The standard tools, classical and modern, each fail quantifiably: probing is punished before it pays, commitment is fatal at sub-disturbance excitation once adaptation is necessary, optimism degenerates to tie-breaking or pays asymptotically at least twice the optimum, and regret certificates are blind to the worst-case peak in both directions. The optimal law contains no exploration mechanism, its learning purely passive. These results give the first exact optimality certificate for consistent model chasing as a design principle for adversarial adaptive control.
Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.LG).
Categorie arXiv: Systems and Control (eess.SY) ; Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2608.13651 — 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 2026-10-19T02:26:17.817Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).