EUVIMEDEUVIMED entdecken
Crossref

Instance-Dependent Uniform Tail Bounds for Empirical Processes

Sohail Bahmani

IEEE Transactions on Information Theory · 2026-06 · 72 (6) · 4187-4202

DOI: 10.1109/tit.2026.3677108 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Information Theory, 2026-06. Verfasst von Sohail Bahmani. Die Arbeit nennt 35 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We formulate a uniform tail bound for empirical processes indexed by a class of functions, in terms of the individual deviations of the functions rather than the worst-case deviation in the considered class. The tail bound is established by introducing an initial “deflation” step to the standard generic chaining argument. The resulting tail bound is the sum of the complexity of the “deflated function class” in terms of a generalization of Talagrand’s $\gamma $ functional, and the deviation of the function instance, both of which are formulated based on the natural seminorm induced by the corresponding Cramér functions. Leveraging another less demanding natural seminorm, we also show similar bounds, though with implicit dependence on the sample size, in the more general case where finite exponential moments cannot be assumed. We also provide approximations of the tail bounds in terms of the more prevalent Orlicz norms or their “incomplete” versions under suitable moment conditions.

Zitieren

APA

Bahmani, S. (2026). Instance-Dependent Uniform Tail Bounds for Empirical Processes. IEEE Transactions on Information Theory, 72(6), 4187-4202. https://doi.org/10.1109/tit.2026.3677108

Vancouver

Bahmani S. Instance-Dependent Uniform Tail Bounds for Empirical Processes. IEEE Transactions on Information Theory. 2026;72(6):4187-4202. doi:10.1109/tit.2026.3677108

BibTeX
@article{Bahmani2026,
  author = {Bahmani, Sohail},
  title = {Instance-Dependent Uniform Tail Bounds for Empirical Processes},
  journal = {IEEE Transactions on Information Theory},
  year = {2026},
  volume = {72},
  number = {6},
  pages = {4187--4202},
  doi = {10.1109/tit.2026.3677108}
}
Kostenlos starten →