منابع مشابه
Mixing Times for Uniformly Ergodic Markov Chains
Consider the class of discrete time, general state space Markov chains which satist)' a "'uniform ergodicity under sampling" condition. There are many ways to quantify the notion of "mixing time", i.e., time to approach stationarity from a worst initial state. We prove results asserting equivalence (up to universal constants) of different quantifications of mixing time. This work combines three...
متن کاملLearning from uniformly ergodic Markov chains
Evaluation for generalization performance of learning algorithms has been themain thread of machine learning theoretical research. The previous bounds describing the generalization performance of the empirical risk minimization (ERM) algorithm are usually establishedbased on independent and identically distributed (i.i.d.) samples. In this paper we go far beyond this classical framework by esta...
متن کاملA quantitative Mean Ergodic Theorem for uniformly convex Banach spaces
We provide an explicit uniform bound on the local stability of ergodic averages in uniformly convex Banach spaces. Our result can also be viewed as a finitary version in the sense of T. Tao of the Mean Ergodic Theorem for such spaces and so generalizes similar results obtained for Hilbert spaces by Avigad, Gerhardy and Towsner [1] and T. Tao [11].
متن کاملHoe ding's Inequality for Uniformly Ergodic Markov Chains
We provide a generalization of Hoeeding's inequality to partial sums that are derived from a uniformly ergodic Markov chain. Our exponential inequality on the deviation of these sums from their expectation is particularly useful in situations where we require uniform control on the constants appearing in the bound.
متن کاملThe Polya-Gamma Gibbs Sampler for Bayesian Logistic Regression is Uniformly Ergodic
One of the most widely used data augmentation algorithms is Albert and Chib’s (1993) algorithm for Bayesian probit regression. Polson, Scott and Windle (2013) recently introduced an analogous algorithm for Bayesian logistic regression. The main difference between the two is that Albert and Chib’s (1993) truncated normals are replaced by so-called Polya-Gamma random variables. In this note, we e...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Transactions of the American Mathematical Society
سال: 1995
ISSN: 0002-9947
DOI: 10.2307/2154980