arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1808.05334cs.LGcs.ITmath.ITstat.ML
收藏

间接样本的主动分布学习

Active Distribution Learning from Indirect Samples

Carnegie Mellon University(卡内基梅隆大学)

Samarth Gupta, Gauri Joshi, Osman Yağan

摘要:

本文研究了离散型随机变量$X$的概率分布$P_X$的{ \em学习}问题。在每个时间步,我们选择一个可能的$K$函数$g_1, \ldots, g_K$,并观察相应的样本$g_i(X)$。目标是通过使用最小数量的此类连续样本来估计$X$的概率分布。这个问题有几个实际应用,包括非精确信息下的推理和隐私保护统计估计。我们建立了函数$g_1, \ldots, g_K$的渐近相合估计是可能的充分必要条件。我们还推导出估计误差的下限作为总样本的函数,并表明它是有序的实现。利用这些结果,我们提出了一个迭代算法,i)选择函数观察在每一步的基础上过去的意见;和ii)结合所获得的样本估计$p_X$。该算法的性能进行了研究,在各种情况下的数值,并表现出优于基线方法。

英文摘要:

This paper studies the problem of {\em learning} the probability distribution $P_X$ of a discrete random variable $X$ using indirect and sequential samples. At each time step, we choose one of the possible $K$ functions, $g_1, \ldots, g_K$ and observe the corresponding sample $g_i(X)$. The goal is to estimate the probability distribution of $X$ by using a minimum number of such sequential samples. This problem has several real-world applications including inference under non-precise information and privacy-preserving statistical estimation. We establish necessary and sufficient conditions on the functions $g_1, \ldots, g_K$ under which asymptotically consistent estimation is possible. We also derive lower bounds on the estimation error as a function of total samples and show that it is order-wise achievable. Leveraging these results, we propose an iterative algorithm that i) chooses the function to observe at each step based on past observations; and ii) combines the obtained samples to estimate $p_X$. The performance of this algorithm is investigated numerically under various scenarios, and shown to outperform baseline approaches.

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。

↑