arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1503.07940cs.ITcs.DScs.LGmath.ITmath.STstat.TH
收藏

竞争性分布估计

Competitive Distribution Estimation

University of California, San Diego(加州大学圣地亚哥分校)

Alon Orlitsky, Ananda Theertha Suresh

摘要:

从样本中估计未知分布是统计学中的一个基本问题。这个目标的共同的最小-最大公式考虑了一类中所有分布的最佳估计量的性能。它表明,与$n$样本,分布在$k$符号可以学习到KL发散,减少到零的样本大小$n$,但增长无限的字母大小$k$。最小-最大性能可以被视为相对于知道底层分布的预言机的遗憾。我们考虑两个自然和适度的限制神谕的权力。一个是它只知道符号排列的基本分布,另一个是它知道确切的分布,但限于使用自然估计器,将相同的概率分配给样本中出现同样多次的符号。我们表明,在这两种情况下,竞争性的遗憾减少到$\min(k/n,\tilde{\mathcal{O}}(1/\sqrt n))$,一个数量上界一致的每个字母大小。这表明,当分布基本上预先已知时,分布几乎可以被估计,并且当它们完全预先已知但需要通过自然估计器估计时,分布几乎可以被估计。我们还提供了一个估计,在线性时间内运行,并招致竞争遗憾的$\tilde{\mathcal{O}}(\min(k/n,1/\sqrt n))$,并表明,自然估计,这种竞争遗憾是不可避免的。我们还证明了有效性的竞争力估计使用模拟。

英文摘要:

Estimating an unknown distribution from its samples is a fundamental problem in statistics. The common, min-max, formulation of this goal considers the performance of the best estimator over all distributions in a class. It shows that with $n$ samples, distributions over $k$ symbols can be learned to a KL divergence that decreases to zero with the sample size $n$, but grows unboundedly with the alphabet size $k$. Min-max performance can be viewed as regret relative to an oracle that knows the underlying distribution. We consider two natural and modest limits on the oracle's power. One where it knows the underlying distribution only up to symbol permutations, and the other where it knows the exact distribution but is restricted to use natural estimators that assign the same probability to symbols that appeared equally many times in the sample. We show that in both cases the competitive regret reduces to $\min(k/n,\tilde{\mathcal{O}}(1/\sqrt n))$, a quantity upper bounded uniformly for every alphabet size. This shows that distributions can be estimated nearly as well as when they are essentially known in advance, and nearly as well as when they are completely known in advance but need to be estimated via a natural estimator. We also provide an estimator that runs in linear time and incurs competitive regret of $\tilde{\mathcal{O}}(\min(k/n,1/\sqrt n))$, and show that for natural estimators this competitive regret is inevitable. We also demonstrate the effectiveness of competitive estimators using simulations.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑