Theorem 2.2.6 (Hoeffding's inequality for general bounded random variables). Let X₁, XN be independent random variables. Assume that X₁ [m,, M.] for every i. Then, for any t > 0, we have N {(x₁ - EX;) ≥ 1} { i=1 21² Σ(Μ; – m;)2/ Prove Theorem 2.2.6, possibly with some absolute con- Exercise 2.2.7. stant instead of 2 in the tail. Sexp

Algebra & Trigonometry with Analytic Geometry
13th Edition
ISBN:9781133382119
Author:Swokowski
Publisher:Swokowski
Chapter10: Sequences, Series, And Probability
Section10.8: Probability
Problem 64E
icon
Related questions
Question

Finish exercise 2.2.7

Thank you

Theorem 2.2.6 (Hoeffding's inequality for general bounded random variables).
Let X1,..., XN be independent random variables. Assume that X; € [m;, M;] for
every i. Then, for any t > 0, we have
N
212
P (X; – E X;) > t} < exp
E, (M, – m.)²
i=1
Exercise 2.2.7. ** Prove Theorem 2.2.6, possibly with some absolute con-
stant instead of 2 in the tail.
Transcribed Image Text:Theorem 2.2.6 (Hoeffding's inequality for general bounded random variables). Let X1,..., XN be independent random variables. Assume that X; € [m;, M;] for every i. Then, for any t > 0, we have N 212 P (X; – E X;) > t} < exp E, (M, – m.)² i=1 Exercise 2.2.7. ** Prove Theorem 2.2.6, possibly with some absolute con- stant instead of 2 in the tail.
Expert Solution
steps

Step by step

Solved in 3 steps with 15 images

Blurred answer
Recommended textbooks for you
Algebra & Trigonometry with Analytic Geometry
Algebra & Trigonometry with Analytic Geometry
Algebra
ISBN:
9781133382119
Author:
Swokowski
Publisher:
Cengage
Calculus For The Life Sciences
Calculus For The Life Sciences
Calculus
ISBN:
9780321964038
Author:
GREENWELL, Raymond N., RITCHEY, Nathan P., Lial, Margaret L.
Publisher:
Pearson Addison Wesley,