- Probab. Surveys
- Volume 17 (2020), 257-317.
Time-uniform Chernoff bounds via nonnegative supermartingales
We develop a class of exponential bounds for the probability that a martingale sequence crosses a time-dependent linear threshold. Our key insight is that it is both natural and fruitful to formulate exponential concentration inequalities in this way. We illustrate this point by presenting a single assumption and theorem that together unify and strengthen many tail bounds for martingales, including classical inequalities (1960–80) by Bernstein, Bennett, Hoeffding, and Freedman; contemporary inequalities (1980–2000) by Shorack and Wellner, Pinelis, Blackwell, van de Geer, and de la Peña; and several modern inequalities (post-2000) by Khan, Tropp, Bercu and Touati, Delyon, and others. In each of these cases, we give the strongest and most general statements to date, quantifying the time-uniform concentration of scalar, matrix, and Banach-space-valued martingales, under a variety of nonparametric assumptions in discrete and continuous time. In doing so, we bridge the gap between existing line-crossing inequalities, the sequential probability ratio test, the Cramér-Chernoff method, self-normalized processes, and other parts of the literature.
Probab. Surveys, Volume 17 (2020), 257-317.
Received: November 2018
First available in Project Euclid: 20 May 2020
Permanent link to this document
Digital Object Identifier
Primary: 60E15: Inequalities; stochastic orderings 60G17: Sample path properties
Secondary: 60F10: Large deviations 60B20: Random matrices (probabilistic aspects; for algebraic aspects see 15B52)
Howard, Steven R.; Ramdas, Aaditya; McAuliffe, Jon; Sekhon, Jasjeet. Time-uniform Chernoff bounds via nonnegative supermartingales. Probab. Surveys 17 (2020), 257--317. doi:10.1214/18-PS321. https://projecteuclid.org/euclid.ps/1589940218