Consider the problem of nonparametric estimation of an unknown $\beta$-H\"older smooth density $p_{XY}$ at a given point, where $X$ and $Y$ are both $d$ dimensional. An infinite sequence of i.i.d.\ samples $(X_i,Y_i)$ are generated according to this distribution, and two terminals observe $(X_i)$ and $(Y_i)$, respectively. They are allowed to exchange $k$ bits either in oneway or interactively in order for Bob to estimate the unknown density. We show that the minimax mean square risk is order $\left(\frac{k}{\log k} \right)^{-\frac{2\beta}{d+2\beta}}$ for one-way protocols and $k^{-\frac{2\beta}{d+2\beta}}$ for interactive protocols. The logarithmic improvement is nonexistent in the parametric counterparts, and therefore can be regarded as a consequence of nonparametric nature of the problem. Moreover, a few rounds of interactions achieve the interactive minimax rate: the number of rounds can grow as slowly as the super-logarithm (i.e., inverse tetration) of $k$. The proof of the upper bound is based on a novel multi-round scheme for estimating the joint distribution of a pair of biased Bernoulli variables.
翻译:(x_i,Y_i) 样本的无限序列 $(x_i,Y_i) 依此分布生成,两个终端分别观测$(X_i) 美元和$(Y_i) 美元,允许在单程或互动方式上交换美元比特,以便鲍勃估算未知密度。我们显示,最小平均值风险的正方形值为$left(frac{kunlog k}\right)\\\frac\\\\\ beta\\\\\\ $(x_i,Y_i) 。对于一线协议,两个终端分别观测$(X_i) 美元和$(Y_i) 美元和$(Y_i) 美元。它们允许在单程或互动方式上交换美元比特比特。它们不存在对等方的对数改进,因此可以被视为非正向值的平方差值值。 我们显示, 最小正方风险的平方值风险是 $(frac{k}\\\\\\\\\\\\\\\\\\\\\\\\ real maxyal rodeal rodeal rodeal sal sal sal sal sal sal sal sal rovial roduction roduction roduction roduction roduction rodublyal madal roduction roduction macle macle macle madal macle rodudeal macle macle subly) subly subly sublyal subly) subly subly sublyal subal subal suluding subal rodal subal subal 。 suludeal subal subal subalal subal madal subal rodal rodal rodal rodal subal subal suolal sulubal masal subal subal sulu