Country
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
We study how tail properties of the base distribution of a NEF impose limits on the NEF: if the base distribution is subexponential (subgaussian), we show that the NEF is self-concordant with a stretch factor that grows inverse quadratically (respectively, linearly) 2.
Supplemental Information for " Diverse Community Data for Benchmarking Data Privacy Algorithms " October 27, 2023 Supplemental Information Contents
SDNist are intended as tools to encourage investigation and discussion of deiden-tification algorithms, and they are not intended or suitable for product evaluation. The National Institute of Standards and Technology does not endorse any algorithm included in these resources.
Diverse Community Data for Benchmarking Data Privacy Algorithms
Deidentification algorithms are vulnerable to the same bias and privacy issues that impact other data analytics and machine learning applications, and it can even amplify those issues by contaminating downstream applications.
On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets
Different distribution shifts require different algorithmic and operational interventions. Methodological research must be grounded by the specific shifts they address.
HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text
To alleviate the above issues, we propose a simple yet effective framework for producing H igh Q uality black-box hard-label A dversarial Attack, named HQA-Attack . The overview of HQA-Attack is shown in Figure 1. By "high quality", it means that the HQA-Attack method can generate