| { |
| "schema_version": 1, |
| "title": "Repro: Accuracy-First Rényi Differential Privacy and Post-Processing Immunity", |
| "emoji": "🔐", |
| "space_id": "snaykey/repro-one-param-subgroups", |
| "paper": { |
| "openreview_id": "CVDEc0doW8" |
| }, |
| "tags": [ |
| "icml2026-repro", |
| "paper-CVDEc0doW8" |
| ], |
| "updated_at": "2026-07-30T16:00:00+00:00", |
| "root": { |
| "slug": "index", |
| "title": "Reproduction: Accuracy-First Rényi Differential Privacy and Post-Processing Immunity", |
| "file": "pages/index.md", |
| "children": [ |
| { |
| "slug": "claim-1", |
| "title": "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).", |
| "file": "pages/claim-1/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-2", |
| "title": "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).", |
| "file": "pages/claim-2/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-3", |
| "title": "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).", |
| "file": "pages/claim-3/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-4", |
| "title": "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).", |
| "file": "pages/claim-4/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-5", |
| "title": "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).", |
| "file": "pages/claim-5/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "claim-6", |
| "title": "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).", |
| "file": "pages/claim-6/page.md", |
| "children": [] |
| }, |
| { |
| "slug": "conclusion", |
| "title": "Conclusion", |
| "file": "pages/conclusion/page.md", |
| "children": [] |
| } |
| ] |
| } |
| } |
