arXiv:2610. 19573v1 Announce Type: cross Abstract: Differential Privacy (DP) provides a rigorous framework for quantifying privacy guarantees.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
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.
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.
arXiv:2606. 17995v1 Announce Type: cross Abstract: We study the privacy of releasing posterior sample paths from a Gaussian process (GP) when the entire training set including covariates and responses is private.
arXiv:2610.08460v1 Announce Type: new Abstract: We propose a simple framework for constructing differentially private confidence regions \textit{in one shot}, i.e., by adding noise only to the final...
The paper presents a Gaussian approximation for the privacy loss distribution in differentially private stochastic gradient descent (DP‑SGD) when subsampling is used. It shows that, after truncating rare large losses, the privacy loss behaves like a Gaussian with the same mean and variance, up to a small shift that grows only logarithmically with the error tolerance. This leads to tighter variance‑based bounds for subsampled mechanisms, improving upon previous Renyi‑divergence analyses and explaining the effectiveness of the connect‑the‑dots method for random allocation sampling.
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.