The authors give an efficient non-interactive L-LDP algorithm for SCO achieving excess risk O(sqrt(K/(ε n))) in high privacy and O(sqrt(K/(e^ε n))) in medium privacy, with matching information-theoretic lower bounds for large n.
Duchi, Michael I
7 Pith papers cite this work, alongside 516 external citations. Polarity classification is still indexing.
7
Pith papers citing it
516
external citations · Crossref
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 2polarities
background 2representative citing papers
A one-to-one correspondence maps maximal LDP channels under the Blackwell order to vertices of a finite-dimensional polytope, making optimal privacy-utility trade-offs computable via linear programming or vertex enumeration for general problems.
mPL measures attacker-aligned privacy leakage from joint data releases and AmPL provides an adaptive way to bound it with low utility cost in ML settings.
Using the shuffle index, the authors formulate and solve an optimization problem for post-shuffle minimax-optimal unbiased mean estimation, yielding an asymptotically optimal mechanism whose privacy-utility tradeoff approaches the central Gaussian mechanism in the high-privacy regime.
Causality provides a unifying framework for resolving trade-offs in trustworthy AI by managing invariance conflicts under changes to the data-generating process.
Sufficient conditions using the Wasserstein metric of order 1 are derived to calibrate Laplace noise for pufferfish privacy in multi-user aggregated queries, with relaxations for binary data that reduce noise while preserving indistinguishability.
A cross-platform mobile application deploys an ensemble of quantized open-source LLMs for fully local, DSM-5-aligned psychiatric decision support with claimed accuracy comparable to prior cloud versions.
citing papers explorer
-
Convex Optimization with Local Label Differential Privacy: Tight Bounds in All Privacy Regimes
The authors give an efficient non-interactive L-LDP algorithm for SCO achieving excess risk O(sqrt(K/(ε n))) in high privacy and O(sqrt(K/(e^ε n))) in medium privacy, with matching information-theoretic lower bounds for large n.
-
Optimal Privacy-Utility Trade-Offs in LDP: Functional and Geometric Perspectives
A one-to-one correspondence maps maximal LDP channels under the Blackwell order to vertices of a finite-dimensional polytope, making optimal privacy-utility trade-offs computable via linear programming or vertex enumeration for general problems.
-
Metric-Normalized Posterior Leakage (mPL): Attacker-Aligned Privacy for Joint Consumption
mPL measures attacker-aligned privacy leakage from joint data releases and AmPL provides an adaptive way to bound it with low utility cost in ML settings.
-
Shuffling-Aware Optimization for Private Vector Mean Estimation
Using the shuffle index, the authors formulate and solve an optimization problem for post-shuffle minimax-optimal unbiased mean estimation, yielding an asymptotically optimal mechanism whose privacy-utility tradeoff approaches the central Gaussian mechanism in the high-privacy regime.
-
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
Causality provides a unifying framework for resolving trade-offs in trustworthy AI by managing invariance conflicts under changes to the data-generating process.
-
Multi-user Pufferfish Privacy
Sufficient conditions using the Wasserstein metric of order 1 are derived to calibrate Laplace noise for pufferfish privacy in multi-user aggregated queries, with relaxations for binary data that reduce noise while preserving indistinguishability.
-
Toward Zero-Egress Psychiatric AI: On-Device LLM Deployment for Privacy-Preserving Mental Health Decision Support
A cross-platform mobile application deploys an ensemble of quantized open-source LLMs for fully local, DSM-5-aligned psychiatric decision support with claimed accuracy comparable to prior cloud versions.