完美隐私下的信息瓶颈
Information Bottleneck under Perfect Privacy
浏览论文内容
中文总结 AI 辅助
该研究针对完美隐私下的信息瓶颈问题,提出基于ADMM的定制化优化方法,在正则性条件下证明其全局收敛性并表征收敛速率,扩展至不精确块更新分析,解决了经典速率-相关性权衡外的隐私约束优化问题。
中文摘要 AI 辅助
本研究探讨完美隐私约束下的信息瓶颈问题,重点关注主动速率 regime(表示速率约束起作用并直接限制可实现效用的场景)。研究目标是构建一种表示,在保留与效用相关信息的同时,与敏感变量保持统计独立。这种精确独立性要求在经典的速率-相关性权衡之外引入了额外约束,必须明确纳入优化过程。为此,研究人员开发了一种针对该问题结构量身定制的、基于交替方向乘子法(ADMM)的方法。在合适的正则性条件下,证明了生成序列的全局收敛性,通过 Kurdyka-Lojasiewicz 指数表征了其收敛速率,并将分析扩展至不精确的块更新场景。
英文摘要
In this work, we study the information bottleneck under perfect privacy, with particular emphasis on the active-rate regime, where the representation-rate constraint is binding and directly limits the achievable utility. The goal is to construct a representation that preserves utility-relevant information while remaining statistically independent of a sensitive variable. This exact independence requirement introduces an additional constraint beyond the classical rate-relevance tradeoff and must be explicitly incorporated into the optimization. To this end, we develop an alternating direction method of multipliers (ADMM)-based method tailored to the resulting problem structure. Under suitable regularity conditions, we establish global convergence of the generated sequence, characterize its convergence rate through the Kurdyka-Lojasiewicz exponent, and extend the analysis to inexact block updates.
发表机构
- Laboratoire des Signaux et Systèmes (L2S)(信号与系统实验室(L2S))
- CNRS(法国国家科学研究中心)
- CentraleSupélec(中央理工-高等电力学院)
- Université Paris-Saclay(巴黎萨克雷大学)
机构由 AI 辅助整理,请以论文原文为准。