Improved concentration bounds for sums of independent sub-exponential random variables
Iosif Pinelis

TL;DR
This paper improves Bernstein-type bounds on the tail probabilities for sums of independent zero-mean sub-exponential variables, achieving tighter bounds with optimality features.
Contribution
It introduces improved concentration bounds for sums of sub-exponential variables with enhanced optimality properties.
Findings
Tighter tail probability bounds established
Bounds demonstrate near-optimality
Applicable to sums of independent sub-exponential variables
Abstract
Known Bernstein-type upper bounds on the tail probabilities for sums of independent zero-mean sub-exponential random variables are improved in several ways at once. The new upper bounds have a certain optimality property.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsProbability and Risk Models · Distributed Sensor Networks and Detection Algorithms · Statistical Methods and Inference
