Mathematics – Probability
Scientific paper
2010-04-25
Mathematics
Probability
Current paper is the version of record. The material on Freedman's inequality has been moved to a separate note; other marting
Scientific paper
This paper presents new probability inequalities for sums of independent, random, self-adjoint matrices. These results place simple and easily verifiable hypotheses on the summands, and they deliver strong conclusions about the large-deviation behavior of the maximum eigenvalue of the sum. Tail bounds for the norm of a sum of random rectangular matrices follow as an immediate corollary. The proof techniques also yield some information about matrix-valued martingales. In other words, this paper provides noncommutative generalizations of the classical bounds associated with the names Azuma, Bennett, Bernstein, Chernoff, Hoeffding, and McDiarmid. The matrix inequalities promise the same diversity of application, ease of use, and strength of conclusion that have made the scalar inequalities so valuable.
No associations
LandOfFree
User-friendly tail bounds for sums of random matrices does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with User-friendly tail bounds for sums of random matrices, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and User-friendly tail bounds for sums of random matrices will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-31638