Metraipolis › archive › dc_680e35484fb0

Agnostic Smoothed Online Regression with Adversarial Responses — arXiv:2609.32478

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32478
License (as archived)
CC0-1.0
Archived
2026-10-07T22:39:40.017Z
SHA-256 of the archived text
052c473ffffae1981b1e8cca59c75fcc95c3a2b492c0338b867fe32d53448f60
Stable URL of this page
https://metraipolis.com/documento/dc_680e35484fb0

How to cite

Agnostic Smoothed Online Regression with Adversarial Responses — arXiv:2609.32478 — arXiv (en), https://arxiv.org/abs/2609.32478 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_680e35484fb0 (Metraipolis archive dc_680e35484fb0, sha256 052c473ffffae1981b1e8cca59c75fcc95c3a2b492c0338b867fe32d53448f60)
BibTeX
@misc{dc680e35484fb0,
  title = {Agnostic Smoothed Online Regression with Adversarial Responses — arXiv:2609.32478},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32478},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_680e35484fb0; sha256 052c473ffffae1981b1e8cca59c75fcc95c3a2b492c0338b867fe32d53448f60},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32478. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study smoothed online prediction with bounded adversarial responses. This widely studied framework bridges i.i.d. sampling and adversarial covariate selection through a smoothness parameter $\textsf{C}_{\textsf{cov}}$, which bounds conditional covariate densities relative to a fixed, unknown base measure. We propose \textsc{Hedge-Cover}, an information-theoretic algorithm that achieves sublinear regret $\widetilde{O}(\sqrt{\text{Pdim}(\mathcal{F}) \textsf{C}_{\textsf{cov}} T})$ for function classes with bounded pseudo-dimension. The algorithm aggregates a carefully constructed family of experts using \textsc{Hedge}, with a prior that links regret to the number of disagreements between a consistent selector and a target function. We bound this number by exploiting covariate smoothness. This answers an open problem posed in \cite{blanchard2025agnostic} on the minimax optimal adaptive regret of the smoothed online regression problem. We establish a matching lower bound for the class of linear predictors. The main intricacy of the lower bound lies in explicitly constructing a challenging sequential covariate distribution supported on mutually orthogonal hyperplanes. This construction may be of independent technical interest. Finally, we revisit the well-specified setting and quantify the effect of response noise. For conditionally $\nu^2$-subGaussian responses, we extend the existing lower bound under realizable responses by showing that the minimax expected regret is $\Omega((1\vee \nu)\sqrt{(\textsf{C}_{\textsf{cov}}-1)dT})$ for a function class of VC dimension $d$. A corresponding upper bound for ERM matches this dependence on $\nu$.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST).
Pagina del lavoro: https://arxiv.org/abs/2609.32478 — 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 2026-10-07T22:14:28.606Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).