Results 271 to 280 of about 51,964 (316)

Almost sure convergence

Journal of the American Statistical Association, 1974
W. Stout
semanticscholar   +2 more sources

Uniform almost sure convergence and asymptotic distribution of the wavelet-based estimators of partial derivatives of multivariate density function under weak dependence

, 2021
This paper is devoted to the estimation of partial derivatives of multivariate density functions. In this regard, nonparametric linear wavelet-based estimators are introduced, showing their attractive properties from the theoretical point of view.
Soumaya Allaoui, Salim Bouzebda, C. Chesneau, Jicheng Liu   +3 more
semanticscholar   +1 more source

On the almost sure convergence for sums of negatively superadditive dependent random vectors in Hilbert spaces and its application

Communications in Statistics - Theory and Methods, 2020
This paper develops almost sure convergence for sums of negatively superadditive dependent random vectors in Hilbert spaces, we obtain Chung type SLLN and the Jaite type SLLN for sequences of negatively superadditive dependent random vectors in Hilbert ...
Son Cong Ta, Cuong Manh Tran, D. Le
semanticscholar   +1 more source

Almost Sure Convergence in Extreme Value Theory

Mathematische Nachrichten, 1998
AbstractLet X1, …, Xn be independent random variables with common distribution function F. Define equation image and let G(x) be one of the extreme‐value distributions. Assume F ∈ D(G), i.e., there exist an> 0 and bn ∈ ℝ such that equation image .Let l(−∞,x)(·) denote the indicator function of the set (−∞,x) and S(G) =: {x : 0 < G(x) < 1 ...
Cheng, Shihong, Peng, Liang, Qi, Yongcheng   +2 more
openaire   +2 more sources

Almost sure convergence for weighted sums of φ-mixing random variables with applications

Communications in Statistics - Theory and Methods, 2019
For a sequence of -mixing random variables and a triangular array of constants conditions are given to ensure that where is a prescribed sequence of positive constants.
J. Lita da Silva
semanticscholar   +1 more source

Almost sure convergence of random gossip algorithms

2007 46th IEEE Conference on Decision and Control, 2007
In this paper we provide a proof of almost sure convergence to consensus for an extremely general class of edge selection processes. The proof also applies to continuous time gossip algorithms.
PICCI, GIORGIO, TAYLOR T. J.
openaire   +2 more sources

Ensuring Both Almost Sure Convergence and Differential Privacy in Nash Equilibrium Seeking on Directed Graphs

IEEE Transactions on Automatic Control
We propose a distributed Nash equilibrium seeking approach that can achieve both almost sure convergence and rigorous differential privacy with finite cumulative privacy budget, which is in sharp contrast to existing differential-privacy solutions for ...
Yongqiang Wang, Tamer Başar
semanticscholar   +1 more source

Almost Sure Convergence Rates and Concentration of Stochastic Approximation and Reinforcement Learning with Markovian Noise

arXiv.org
This paper establishes the first almost sure convergence rate and the first maximal concentration bound with exponential tails for general contractive stochastic approximation algorithms with Markovian noise.
Xiaochi Qian, Zixuan Xie, Xinyu Liu, Shangtong Zhang   +3 more
semanticscholar   +1 more source

Almost sure convergence rates of stochastic gradient methods under gradient domination

arXiv.org
Stochastic gradient methods are among the most important algorithms in training machine learning problems. While classical assumptions such as strong convexity allow a simple analysis they are rarely satisfied in applications. In recent years, global and
Simon Weissmann, Sara Klein, Waïss Azizian, Leif Döring   +3 more
semanticscholar   +1 more source

Summability methods and almost sure convergence

Zeitschrift f�r Wahrscheinlichkeitstheorie und Verwandte Gebiete, 1985
The authors investigate almost sure convergence for sequences of i.i.d. random variables under different methods of summability. We say \(s_ n\to s\) (P), if \(\sum^{\infty}_{j=0}s_ jP(S_ n=j)\to s\) as \(n\to \infty\), where \(S_ n:=\xi_ 1+...+\xi_ n\), and \(\xi_ 1,\xi_ 2,..\). are integer-valued independent random variables.
Bingham, N. H., Maejima, Makoto
openaire   +2 more sources