Phase transitions in nonparametric regressions
研究了单变量非参数回归中，当样本量n与光滑度γ+1满足不同关系时，极小极大最优均方积分误差（MISE）速率发生相变，并给出了新的度量熵界。
When the unknown regression function of a single variable is known to have derivatives up to the (γ+1)th order bounded in absolute values by a common constant everywhere or a.e. (i.e., (γ+1)th degree of smoothness), the minimax optimal rate of the mean integrated squared error (MISE) is stated as 1n2γ+22γ+3 in the literature. This paper shows that: (i) if n≤γ+12γ+3, the minimax optimal MISE rate is lognnlog(logn) and the optimal degree of smoothness to exploit is roughly maxlogn2loglogn,1; (ii) if n>γ+12γ+3, the minimax optimal MISE rate is 1n2γ+22γ+3 and the optimal degree of smoothness to exploit is γ+1. The fundamental contribution of this paper is a set of metric entropy bounds we develop for smooth function classes. Some of our bounds are original, and some of them improve and/or generalize the ones in the literature (e.g., Kolmogorov and Tikhomirov, 1959). Our metric entropy bounds allow us to show phase transitions in the minimax optimal MISE rates associated with some commonly seen smoothness classes as well as non-standard smoothness classes, and can also be of independent interest outside the nonparametric regression problems.