Top Qs
Timeline
Chat
Perspective
Hoeffding's inequality
Probabilistic inequality applying on sum of bounded random variables From Wikipedia, the free encyclopedia
Remove ads
In probability theory, Hoeffding's inequality provides an upper bound on the probability that the sum of bounded independent random variables deviates from its expected value by more than a certain amount. Hoeffding's inequality was proven by Wassily Hoeffding in 1963.[1]
Hoeffding's inequality is a special case of the Azuma–Hoeffding inequality and McDiarmid's inequality. It is similar to the Chernoff bound, but tends to be less sharp, in particular when the variance of the random variables is small.[2] It is similar to, but incomparable with, one of Bernstein's inequalities.
Remove ads
Statement
Summarize
Perspective
Let X1, ..., Xn be independent random variables such that almost surely. Consider the sum of these random variables,
Then Hoeffding's theorem states that, for all t > 0,[3]
Here E[Sn] is the expected value of Sn.
Note that the inequalities also hold when the Xi have been obtained using sampling without replacement; in this case the random variables are not independent anymore. A proof of this statement can be found in Hoeffding's paper. For slightly better bounds in the case of sampling without replacement, see for instance the paper by Serfling (1974).
Generalization
Let be independent observations such that and . Let . Then, for any ,[4]
Special Case: Bernoulli RVs
Suppose and for all i. This can occur when Xi are independent Bernoulli random variables, though they need not be identically distributed. Then we get the inequality[5]
or equivalently,
for all . This is a version of the additive Chernoff bound which is more general, since it allows for random variables that take values between zero and one, but also weaker, since the Chernoff bound gives a better tail bound when the random variables have small variance.
Remove ads
General case of bounded from above random variables
Summarize
Perspective
Hoeffding's inequality can be extended to the case of bounded from above random variables.[6]
Let X1, ..., Xn be independent random variables such that and almost surely. Denote by
Hoeffding's inequality for bounded from above random variables states that for all ,
In particular, if for all , then for all ,
Remove ads
General case of sub-Gaussian random variables
Summarize
Perspective
The proof of Hoeffding's inequality can be generalized to any sub-Gaussian distribution. Recall that a random variable X is called sub-Gaussian,[7] if
for some . For any bounded variable X, for for some sufficiently large T. Then for all so taking yields
for . So every bounded variable is sub-Gaussian.
For a random variable X, the following norm is finite if and only if X is sub-Gaussian:
Then let X1, ..., Xn be independent sub-Gaussian random variables, the general version of the Hoeffding's inequality states that:
where c > 0 is an absolute constant.[8]
Equivalently, we can define sub-Gaussian distributions by variance proxy, defined as follows. If there exists some such that for all , then is called a variance proxy, and the smallest such is called the optimal variance proxy, and denoted by . In this form, Hoeffding's inequality states
Remove ads
Proof
Summarize
Perspective
We quote:
Hoeffding's lemma—Suppose X is a real random variable such that almost surely. Then
The proof of Hoeffding's inequality then follows similarly to concentration inequalities like Chernoff bounds.[9]
Proof
As in the theorem statement, suppose X1, ..., Xn are n independent random variables such that almost surely for all i, and let .
Then for s, t > 0, Markov's inequality and the independence of Xi implies:
This upper bound is the best for the value of s minimizing the value inside the exponential. This can be done easily by optimizing a quadratic, giving
Writing the above bound for this value of s, we get the desired bound:
This proof easily generalizes to the case for sub-Gaussian distributions with variance proxy.
Remove ads
Usage
Summarize
Perspective
Confidence intervals
Hoeffding's inequality can be used to derive confidence intervals. We consider a coin that shows heads with probability p and tails with probability 1 − p. We toss the coin n times, generating n samples (which are i.i.d Bernoulli random variables). The expected number of times the coin comes up heads is pn. Furthermore, the probability that the coin comes up heads at least k times can be exactly quantified by the following expression:
where H(n) is the number of heads in n coin tosses.
When k = (p + ε)n for some ε > 0, Hoeffding's inequality bounds this probability by a term that is exponentially small in ε2n:
Since this bound holds on both sides of the mean, Hoeffding's inequality implies that the number of heads that we see is concentrated around its mean, with exponentially small tail.
Thinking of as the "observed" mean, this probability can be interpreted as the level of significance (probability of making an error) for a confidence interval around of size 2ɛ:
Finding n for opposite inequality sign in the above, i.e. n that violates inequality but not equality above, gives us:
Therefore, we require at least samples to acquire a -confidence interval .
Hence, the cost of acquiring the confidence interval is sublinear in terms of confidence level and quadratic in terms of precision. Note that there are more efficient methods of estimating a confidence interval.
Remove ads
See also
- Concentration inequality – a summary of tail-bounds on random variables.
- Hoeffding's lemma
- Bernstein inequalities (probability theory)
Notes
References
Wikiwand - on
Seamless Wikipedia browsing. On steroids.
Remove ads