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 2502.16352cs.LGcs.CRcs.CYcs.DS
收藏

有限披露下的分类验证

Verifying Classification with Limited Disclosure

Siddharth Bhandari, Liren Shan

AI总结:

针对多参与方分类验证问题,提出基于留一法维度的验证协议,刻画线性分类器间隔与披露文档数的三分法权衡,并扩展到不可实现与容错场景。

摘要:

我们考虑由Dong、Hartline和Vijayaraghavan(2022)提出的多参与方分类问题,该问题受电子发现(e-discovery)场景启发。在此问题中,我们的目标是设计一个协议,保证请求方能够获得几乎所有相关文档,同时最小化不相关文档的披露。我们开发了验证协议,通过披露少量不相关文档来证明分类器的正确性。\n我们引入了一个称为分类器族“留一法维度”(Leave-One-Out dimension)的组合学概念,并证明在可实现(realizable)设置下(即该族中存在完美分类器),我们的协议所披露的不相关文档数量至多等于该维度。对于具有间隔(margin)的线性分类器,我们刻画了间隔与验证所需披露的不相关文档数量之间的权衡关系。具体而言,我们建立了这一需求的三分法:对于$d$维实例,当间隔大于$1/3$时,仅需披露$O(1)$个不相关文档即可完成验证;当间隔恰好等于$1/3$时,在最坏情况下至少需要披露$\Omega(d)$个不相关文档;当间隔小于$1/3$时,验证需要披露$\Omega(e^d)$个不相关文档。我们相信这一结果具有独立价值,可应用于编码理论和组合几何。我们进一步将协议扩展到不可实现(nonrealizable)设置,定义了类似的组合量“鲁棒留一法维度”(robust Leave-One-Out dimension),并扩展到协议能够容忍Alice误分类错误的场景。

英文摘要:

We consider the multi-party classification problem introduced by Dong, Hartline, and Vijayaraghavan (2022) motivated by electronic discovery. In this problem, our goal is to design a protocol that guarantees the requesting party receives nearly all responsive documents while minimizing the disclosure of nonresponsive documents. We develop verification protocols that certify the correctness of a classifier by disclosing a few nonresponsive documents. We introduce a combinatorial notion called the Leave-One-Out dimension of a family of classifiers and show that the number of nonresponsive documents disclosed by our protocol is at most this dimension in the realizable setting, where a perfect classifier exists in this family. For linear classifiers with a margin, we characterize the trade-off between the margin and the number of nonresponsive documents that must be disclosed for verification. Specifically, we establish a trichotomy in this requirement: for $d$ dimensional instances, when the margin exceeds $1/3$, verification can be achieved by revealing only $O(1)$ nonresponsive documents; when the margin is exactly $1/3$, in the worst case, at least $Ω(d)$ nonresponsive documents must be disclosed; when the margin is smaller than $1/3$, verification requires $Ω(e^d)$ nonresponsive documents. We believe this result is of independent interest with applications to coding theory and combinatorial geometry. We further extend our protocols to the nonrealizable setting defining an analogous combinatorial quantity robust Leave-One-Out dimension, and to scenarios where the protocol is tolerant to misclassification errors by Alice.

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。

↑