Poster

Time-uniform confidence bands for the CDF under nonstationarity

Paul Mineiro · Steven Howard

Great Hall & Hall B1+B2 (level 1) #902
[ ]
Tue 12 Dec 3:15 p.m. PST — 5:15 p.m. PST

Abstract:

Estimation of a complete univariate distribution from a sequence of observations is a useful primitive for both manual and automated decision making. This problem has received extensive attention in the i.i.d. setting, but the arbitrary data dependent setting remains largely unaddressed. We present computationally felicitous time-uniform and value-uniform bounds on the CDF of the running averaged conditional distribution of a sequence of real-valued random variables. Consistent with known impossibility results, our CDF bounds are always valid but sometimes trivial when the instance is too hard, and we give an instance-dependent convergence guarantee. The importance-weighted extension is appropriate for estimating complete counterfactual distributions of rewards given data from a randomized experiment, e.g., from an A/B test or a contextual bandit.

Chat is not available.