ProCreations's picture
Publish validated ICML reproduction
82524c9 verified
Raw
History Blame Contribute Delete
1.43 kB
[
"The paper reformulates mechanisms as returning pairs (y, ε) rather than separate output and privacy-loss functions, resolving prior notational obstacles to defining post-processing immunity for accuracy-first privacy (Section 3.1).",
"Pure ex-post privacy (δ=0) satisfies post-processing immunity, but δ-probabilistic ex-post privacy with δ>0 does not, even though the latter is shown equivalent to (ε,δ)-probabilistic differential privacy for constant ε (Theorem 3.2, Section 3.2).",
"The paper introduces α-ex-post Rényi differential privacy (Section 4), proves it satisfies post-processing immunity (Theorem 4), and proves it composes adaptively with total privacy loss ε* = Σε_i (Theorem 6).",
"The sequential precision-weighted Gaussian mechanism (Algorithm 2, Appendix C.4) is shown to achieve α-ex-post RDP equivalent to the original Brownian mechanism (Theorem 5, Section 5).",
"Table 1 summarizes that pure ex-post privacy has post-processing immunity but the Brownian mechanism does not satisfy it, whereas α-ex-post RDP satisfies both post-processing immunity and compatibility with the Brownian mechanism (Table 1, Section 3).",
"On the Adult dataset, a data-dependent stopping rule (Algorithm 1) using a private validation set generates synthetic data while minimizing privacy budget over ε ∈ [0.01, 1] subject to maintaining classifier accuracy thresholds (Figure 1, Section 6)."
]