We determine the exact minimax rate of a Gaussian sequence model under bounded convex constraints, purely in terms of the local geometry of the given constraint set $K$. Our main result shows that the minimax risk (up to constant factors) under the squared $\ell_2$ loss is given by $\epsilon^{ *2} \wedge \operatorname{ diam}(K)^2$ with \begin{ align*} \epsilon^* = \sup \bigg\{ \epsilon : \frac{ \epsilon^2}{ \sigma^2} \leq \log M^{ \operatorname{ loc}}(\epsilon)\bigg\}, \end{ align*} where $\log M^{ \operatorname{ loc}}(\epsilon)$ denotes the local entropy of the set $K$, and $\sigma^2$ is the variance of the noise. We utilize our abstract result to re-derive known minimax rates for some special sets $K$ such as hyperrectangles, ellipses, and more generally quadratically convex orthosymmetric sets. Finally, we extend our results to the unbounded case with known $\sigma^2$ to show that the minimax rate in that case is $\epsilon^{ *2}$.

Categories: math.ST stat.TH

On the minimax rate of the Gaussian sequence model under bounded convex constraints