Influence Diagnostics under Self-concordance
Influence Diagnostics under Self-concordance
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Jillian R. Fisher;Lang Liu;Krishna Pillutla;Y. Choi;Zaïd Harchaoui
中科院分区：
文献类型：
--
作者：
Jillian R. Fisher;Lang Liu;Krishna Pillutla;Y. Choi;Zaïd Harchaoui
影响诊断，例如影响函数和近似最大影响扰动，在机器学习和人工智能领域应用中很受欢迎。影响诊断是强大的统计工具，用于识别有影响力的数据点或数据点子集。我们利用高效的逆黑塞向量积实现，为影响函数和近似最大影响扰动建立了有限样本统计界限以及计算复杂度界限。我们用广义线性模型以及基于大型注意力的模型在合成数据和真实数据上说明了我们的结果。
Influence diagnostics such as influence functions and approximate maximum influence perturbations are popular in machine learning and in AI domain applications. Influence diagnostics are powerful statistical tools to identify influential datapoints or subsets of datapoints. We establish finite-sample statistical bounds, as well as computational complexity bounds, for influence functions and approximate maximum influence perturbations using efficient inverse-Hessian-vector product implementations. We illustrate our results with generalized linear models and large attention based models on synthetic and real data.