Concept
Gaussian Arms with Common Variance
A standard model setting in the theoretical analysis of best-arm identification, in which each arm's reward follows a Gaussian distribution with the same variance and unknown mean. It simplifies the error exponent analysis so that it depends only on mean gaps.
Timeline (last 90 days)
Oct 16
The common-variance Gaussian arm model is a standard setting in theoretical analysis of BAI: each arm's reward follows a Gaussian distribution with the same variance and an unknown mean.
Unverified50%