General lower bounds for interactive high-dimensional estimation under information constraints.

General lower bounds for interactive high-dimensional estimation under information constraints.
复制标题

信息约束下交互式高维估计的一般下界。

DOI:
--
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Himanshu Tyagi
Himanshu Tyagi
中科院分区:
--
文献类型:
--
作者:
Jayadev Acharya;C. Canonne;Himanshu Tyagi

文献摘要

参考文献

被引文献

相似文献

我们认为分布式参数估计的任务,使用顺序交互式协议的本地信息的限制,如带宽限制,本地差分隐私,和限制测量。我们提供了一个一般的框架,使我们能够推导出各种(紧)极大极小下界下的分布,连续和离散的不同参数的家庭,在任何$\ell_p$损失。我们的下限框架是通用的,并产生“即插即用”的界限,广泛适用于大范围的估计问题。特别是,我们的方法恢复使用数据处理不等式和Cram\'er-Rao界,其他两种方法证明在我们感兴趣的设置下界得到的界限。此外,对于所考虑的家庭,我们用匹配的上界来补充我们的下界。
We consider the task of distributed parameter estimation using sequentially interactive protocols subject to local information constraints such as bandwidth limitations, local differential privacy, and restricted measurements. We provide a general framework enabling us to derive a variety of (tight) minimax lower bounds under different parametric families of distributions, both continuous and discrete, under any $\ell_p$ loss. Our lower bound framework is versatile, and yields "plug-and-play" bounds that are widely applicable to a large range of estimation problems. In particular, our approach recovers bounds obtained using data processing inequalities and Cram\'er-Rao bounds, two other alternative approaches for proving lower bounds in our setting of interest. Further, for the families considered, we complement our lower bounds with matching upper bounds.
DOI: --
发表时间: 2019
期刊: Abstracts of papers - IEEE International Symposium on Information Theory
影响因子: --
作者:
Leighton Pate Barnes, Yanjun Han
通讯作者: Leighton Pate Barnes, Yanjun Han
DOI: 10.1109/tit.2020.3028440
发表时间: 2018-12
影响因子: 2.5
作者:
Jayadev Acharya;C. Canonne;Himanshu Tyagi
通讯作者: Jayadev Acharya;C. Canonne;Himanshu Tyagi
本地差异隐私下的 Fisher 信息
DOI: 10.1109/jsait.2020.3039461
发表时间: 2020
期刊: IEEE Journal on Selected Areas in Information Theory
影响因子: --
作者:
Barnes, Leighton Pate;Chen, Wei-Ning;Ozgur, Ayfer
通讯作者: Ozgur, Ayfer
DOI: --
发表时间: 2020
期刊: Advances in Neural Information Processing Systems
影响因子: --
作者:
Canonne, Clement;Kamath, Guatam;McMillan, Audra;Ullman, Jonathan;Zakynthinou, Lydia
通讯作者: Zakynthinou, Lydia