arXiv Machine Learning
Jun 9
Differentially Private Range Subgraph Counting
arXiv:2606. 08179v1 Announce Type: cross Abstract: Subgraph counting is a fundamental problem in graph analysis.
Fixed-Parameter Tractability of Private Synthetic Data Generation
arXiv:2606. 11283v1 Announce Type: cross Abstract: We study the problem of generating synthetic data under differential privacy.
Related stories
arXiv Machine Learning
Jun 5
Minimax optimal differentially private synthetic data for smooth queries
arXiv:2602. 01607v3 Announce Type: replace-cross Abstract: Differentially private synthetic data enables the sharing and analysis of sensitive datasets while providing rigorous privacy guarantees for individual contributors.
arXiv Machine Learning
Jul 7
Efficient privacy loss accounting for subsampling and random allocation
arXiv:2602. 17284v2 Announce Type: replace Abstract: We consider the privacy amplification properties of a sampling scheme in which a user's data isused in $k$ steps chosen randomly and uniformly from a sequence (or set) of $t$ steps.
arXiv Machine Learning
4d ago
Understanding Private Evolution as Learning-Augmented Clustering
arXiv:2609.36678v1 Announce Type: new Abstract: Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm,...
arXiv Machine Learning
Aug 12
Information Bottleneck under Perfect Privacy
arXiv:2608. 11003v1 Announce Type: cross Abstract: In this work, we study the information bottleneck under perfect privacy, with particular emphasis on the active-rate regime, where the representation-rate constraint is binding and directly limits the achievable utility.
arXiv AI
Jul 14
Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation
arXiv:2604. 07486v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for synthetic data generation.
Hugging Face Trending Papers
Jun 11
Disparate Impact in Synthetic Data Generation
We revisit the fairness notion of disparate impact for synthetic data generation (SDG), that assesses whether the utility of generated records is the same across sensitive groups. Our approach departs from existing work on fair SDG, that address the problem of correcting for undue biases in the observed distribution, hence redefining SDG as learning a distribution that is not that of the real data.
arXiv Machine Learning
Sep 10
Differentially Private Model-X Knockoffs via Johnson-Lindenstrauss Transform
arXiv:2508.04800v2 Announce Type: replace-cross Abstract: We introduce a novel privatization framework for high-dimensional controlled variable selection. Our framework enables rigorous False Discove...
arXiv Machine Learning
Sep 24
Private Decentralized Optimization with Noise Reduction and Bias Correction
arXiv:2609.27658v1 Announce Type: new Abstract: Private decentralized learning is affected by sampling noise, privacy noise, and decentralized bias under heterogeneous data. We propose Private Recurs...
arXiv Machine Learning
Aug 4
Private Generative Bootstrap via Blocking
arXiv:2608. 02480v1 Announce Type: cross Abstract: With AI systems gaining more access to individuals' information, it is important to protect privacy when reporting statistical answers.
Hugging Face Trending Papers
Aug 3
Private Generative Bootstrap via Blocking
With AI systems gaining more access to individuals' information, it is important to protect privacy when reporting statistical answers. Equally important is to privatize the reporting of uncertainty in such answers.
Hugging Face Trending Papers
5d ago
Understanding Private Evolution as Learning-Augmented Clustering
Private Evolution (PE) is a differentially private algorithm for synthetic data generation. While it can be viewed as a Wasserstein learning algorithm, it performs much better in practice than worst-c...