Timezone: »

Instance-optimal Mean Estimation Under Differential Privacy
Ziyue Huang · Yuting Liang · Ke Yi

Thu Dec 09 12:30 AM -- 02:00 AM (PST) @

Mean estimation under differential privacy is a fundamental problem, but worst-case optimal mechanisms do not offer meaningful utility guarantees in practice when the global sensitivity is very large. Instead, various heuristics have been proposed to reduce the error on real-world data that do not resemble the worst-case instance. This paper takes a principled approach, yielding a mechanism that is instance-optimal in a strong sense. In addition to its theoretical optimality, the mechanism is also simple and practical, and adapts to a variety of data characteristics without the need of parameter tuning. It easily extends to the local and shuffle model as well.

Author Information

Ziyue Huang (Hong Kong University of Science and Technology)
Yuting Liang (Hong Kong University of Science and Technology)
Ke Yi (" Hong Kong University of Science and Technology, Hong Kong")

More from the Same Authors