On Uniform Laws of Large Numbers for Smoothed Empirical Measures
We consider function-indexed smoothed empirical measures on linear metric spaces and focus on uniform laws of large numbers (ULLN) comparable with Glivenko-Cantelli results in the non-smoothed case. Using the random measure process approach we are able to give a set of sufficient conditions for a ULLN which are different from the ones known in the literature and are more close to being necessary.
KeywordsWeak Convergence Empirical Measure Empirical Process Nonparametric Maximum Likelihood Surable Envelope
Unable to display preview. Download preview PDF.
- Gaenssler, P., Ziegler, K., 1994. “A uniform Law of Large Numbers for set-indexed Processes with applications to Empirical and Partial-Sum Processes.” In: Probability in Banach Spaces, 9, J. Hoffmann-Jørgensen, J. Kuelbs, M.B. Marcus, (eds.), Birkhäuser, Boston, pp. 385–400.Google Scholar
- Gaenssler, P., Rost, D., Ziegler, K., 1998. On Random Measure Processes with Application to Smoothed Empirical Processes. In: High Dimensional Probability, 1, Progress in Probability, Vol. 43, E. Eberlein, M. Hahn, M. Talagrand, (eds.), Birkhäuser Boston, Cambridge, MA, pp. 93–102.CrossRefGoogle Scholar