Dudley's theorem: Difference between revisions
No edit summary |
|||
| Line 2: | Line 2: | ||
==History== |
==History== |
||
The result was first stated and proved by V. N. Sudakov, as pointed out in a paper by [[Richard M. |
The result was first stated and proved by V. N. Sudakov, as pointed out in a paper by [[Richard M. Dudley]].<ref>{{Cite conference|url=https://link.springer.com/chapter/10.1007/978-3-319-40519-3_2|title=V. N. Sudakov's work on expected suprema of Gaussian processes|conference=High Dimensional Probability|volume=VII|editor-first1 =Christian|editor-last1=Houdré|editor-first2=David |editor-last2=Mason|editor-first3=Patricia|editor-last3 = Reynaud-Bouret|editor-link3 =Patricia Reynaud-Bouret|editor-first4=Jan|editor-last4=Jan Rosiński|first=Richard|last=Dudley|author-link = Richard M. Dudley|date=2016|pages=37–43}}</ref> Dudley had earlier credited [[Volker Strassen]] with making the connection between entropy and regularity. |
||
==Statement== |
==Statement== |
||
Revision as of 18:46, 6 April 2023
In probability theory, Dudley's theorem is a result relating the expected upper bound and regularity properties of a Gaussian process to its entropy and covariance structure.
History
The result was first stated and proved by V. N. Sudakov, as pointed out in a paper by Richard M. Dudley.[1] Dudley had earlier credited Volker Strassen with making the connection between entropy and regularity.
Statement
Let (Xt)t∈T be a Gaussian process and let dX be the pseudometric on T defined by
![{\displaystyle d_{X}(s,t)={\sqrt {\mathbf {E} {\big [}|X_{s}-X_{t}|^{2}]}}.\,}](https://wikimedia.org/api/rest_v1/media/math/render/svg/770206df9ebe1f1c09dbea1684a2951cbae3309d)
For ε > 0, denote by N(T, dX; ε) the entropy number, i.e. the minimal number of (open) dX-balls of radius ε required to cover T. Then
![{\displaystyle \mathbf {E} \left[\sup _{t\in T}X_{t}\right]\leq 24\int _{0}^{+\infty }{\sqrt {\log N(T,d_{X};\varepsilon )}}\,\mathrm {d} \varepsilon .}](https://wikimedia.org/api/rest_v1/media/math/render/svg/3cb0f5968f253567ccb5f75d5932eb0e68a73cd8)
Furthermore, if the entropy integral on the right-hand side converges, then X has a version with almost all sample path bounded and (uniformly) continuous on (T, dX).
References
- ^ Dudley, Richard (2016). Houdré, Christian; Mason, David; Reynaud-Bouret, Patricia; Jan Rosiński, Jan (eds.). V. N. Sudakov's work on expected suprema of Gaussian processes. High Dimensional Probability. Vol. VII. pp. 37–43.
- Dudley, Richard M. (1967). "The sizes of compact subsets of Hilbert space and continuity of Gaussian processes". Journal of Functional Analysis. 1 (3): 290–330. doi:10.1016/0022-1236(67)90017-1. MR 0220340.
- Ledoux, Michel; Talagrand, Michel (1991). Probability in Banach spaces. Berlin: Springer-Verlag. pp. xii+480. ISBN 3-540-52013-9. MR 1102015. (See chapter 11)