Lecture 15: Chernoff bounds and Sequential detection
ثبت نشده
چکیده
1 Chernoff Bounds 1.1 Bayesian Hypothesis Test A test using log-likelihood ratio statistic has the form, T (Y ) = logL(Y ) T τ. (1) Bound-1: The probability of error Pe is bounded as, Pe ≤ (π0 + π1e )eμT,0(s0)−s0τ , (2) where μT,0(s) = logE0[e ], and μ ′ T,0(s0) = τ . Bound-2: ∀ s ∈ [0, 1], Pe ≤ max(π0, π1e )eμT,0(s)−sτ . (3) Derivation of the above bound: Consider, Pe = π0P0(Γ1) + π1P1(Γ0), = π0 ∫
منابع مشابه
Lecture 2: Matrix Chernoff bounds
The purpose of my second and third lectures is to discuss spectral sparsifiers, which are the second key ingredient in most of the fast Laplacian solvers. In this lecture we will discuss concentration bounds for sums of random matrices, which are an important technical tool underlying the simplest sparsifier construction.
متن کاملLecture 03 : Chernoff Bounds and Intro to Spectral Graph Theory 3 1 . 1 Hoeffding ’ s Inequality
متن کامل
Lecture 5 — September 8 , 2016
1 Overview In the last lecture we took a more in depth look at Chernoff Bounds and introduced subgaussian and subexponential variables. In this lecture we will continue talking about subgaussian variables and related random variables – subexponential and subgamma, and finally we will give a proof of famous Johnson-Lindenstrauss lemma using property of subgaussian/subgamma variables. Definition ...
متن کاملLecturer : David P . Williamson Scribe : Faisal Alkaabneh
Today we will look at a matrix analog of the standard scalar Chernoff bounds. This matrix analog will be used in the next lecture when we talk about graph sparsification. While we’re more interested in the application of the theorem than its proof, it’s still useful to see the similarities and the differences of moving from the proof of the result for scalars to the same result for matrices. Sc...
متن کاملCS 174 Lecture 10 John Canny
But we already saw that some random variables (e.g. the number of balls in a bin) fall off exponentially with distance from the mean. So Markov and Chebyshev are very poor bounds for those kinds of random variables. The Chernoff bound applies to a class of random variables and does give exponential fall-off of probability with distance from the mean. The critical condition that’s needed for a C...
متن کامل