Large deviation exponential inequalities for supermartingales

نویسندگان
چکیده

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Deviation Inequalities for Exponential Jump-diffusion Processes

In this note we obtain deviation inequalities for the law of exponential jump-diffusion processes at a fixed time. Our method relies on convex concentration inequalities obtained by forward/backward stochastic calculus. In the pure jump and pure diffusion cases, it also improves on classical results obtained by direct application of Gaussian and Poisson bounds.

متن کامل

No fast exponential deviation inequalities for the progressive mixture rule

We consider the learning task consisting in predicting as well as the best function in a finite reference set G up to the smallest possible additive term. If R(g) denotes the generalization error of a prediction function g, under reasonable assumptions on the loss function (typically satisfied by the least square loss when the output is bounded), it is known that the progressive mixture rule ĝ ...

متن کامل

Large Deviation Inequalities for Sums of Indicator Variables

Some new Chernoo type bounds are given for the tail probabilities P(X ?EX a) and P(X ?EX a) when X is a random variable that can be written as a sum of indicator variables that are either independent or negatively related. Several previously known bounds are included and some comparisons are made.

متن کامل

Poisson point processes: large deviation inequalities for the convex distance

An analogue of Talagrand’s convex distance for binomial and Poisson point processes is defined. A corresponding large deviation inequality is proved.

متن کامل

On Probability and Moment Inequalities for Supermartingales and Martingales∗

(Translated by the author) Abstract. The probability inequality for maxk≤n Sk, where Sk = ∑k j=1 Xj , is proved under the assumption that the sequence Sk, k = 1, . . . , n is a supermartingale. This inequality is stated in terms of probabilities P(Xj > y) and conditional variances of random variables Xj , j = 1, . . . , n. As a simple consequence the well-known moment inequality due to Burkhold...

متن کامل

ذخیره 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: Electronic Communications in Probability

سال: 2012

ISSN: 1083-589X

DOI: 10.1214/ecp.v17-2318