arXiv subjects

Ethan Leeman

Publications and source records attributed to Ethan Leeman.

9 recordsLinked to original sources

arXiv2026

Online Differentially Private Consistent Clustering

We study differentially private (DP) $k$-means and $k$-median clustering in the online streaming setting. In this model, points arrive sequentially, and at each time step, we need to output a set of $k$ centers that optimizes the clustering objective for all points seen so far. We give a generic reduction that transforms the (sensitive) input stream into a private stream, which is a semi-coreset of the input stream. This implies that any (non-private) online clustering algorithm, run as a post-processing step, can achieve good utility for the original clustering objective. Our algorithm matches or improves upon the approximation ratio, space usage, and running time of existing algorithms [Epasto et al., 2026, Dupr\'e la Tour et al., 2024]. A key aspect of our reduction is that it inherits desirable properties of the underlying non-private clustering algorithm, such as consistency [Lattanzi and Vassilvitskii, 2017]--a property not satisfied by previous DP algorithms.

cs.DS↗

arXiv2026

Privacy Filters are Captured by Residues: A Characterization of Free Natural Filters and the Cost of Adaptivity

We study privacy filters, which enable privacy accounting for differentially private (DP) mechanisms with adaptively chosen privacy characteristics. We develop a general theory that characterizes the worst-case privacy loss of an interaction involving an analyst that respects some restrictions on what queries they may issue. We apply this theory to develop residue filters, which unifies existing privacy filters. We develop the Gaussian DP (GDP) residue filter, which strictly improves upon the na\"ive GDP filter. We also show that residue filters capture the natural filter, which promises greater utility by leveraging exact privacy accounting techniques. Earlier privacy filters consider only simple privacy parameters such as R\'enyi-DP or GDP parameters. Natural filters account for the entire privacy profile of every query, promising more efficient use of a given privacy budget. We show that, contrary to other forms of DP, natural privacy filters are not free in general. We present a characterization of when a family of private queries admits free natural filters for a given budget. In particular, only families of privacy mechanisms that are totally-ordered when composed admit free natural privacy filters with respect to an arbitrary privacy budget. Finally, we show that, while the natural approximate-DP filter can fail in the presence of adaptive adversary, it cannot fail too badly: the output remains approximate-DP with parameters at most poly-logarithmically worse than the intended privacy parameters.

cs.CR↗

arXiv2025

Nearly-Optimal Private Selection via Gaussian Mechanism

Steinke (2025) recently asked the following intriguing open question: Can we solve the differentially private selection problem with nearly-optimal error by only (adaptively) invoking Gaussian mechanism on low-sensitivity queries? We resolve this question positively. In particular, for a candidate set $\mathcal{Y}$, we achieve error guarantee of $\tilde{O}(\log |\mathcal{Y}|)$, which is within a factor of $(\log \log |\mathcal{Y}|)^{O(1)}$ of the exponential mechanism (McSherry and Talwar, 2007). This improves on Steinke's mechanism which achieves an error of $O(\log^{3/2} |\mathcal{Y}|)$.

cs.CR↗

arXiv2025

Andre-Quillen (co)homology and Equivariant Stable Homotopy Theory

Andr\'e and Quillen introduced a (co)homology theory for augmented commutative rings. Strickland initially proposed some issues with the analogue of the abelianization functor in the equivariant setting. These were resolved by Hill who further gave the notion of a genuine derivation and a module of K\"ahler differentials. We build on this endeavor by expanding to incomplete Tambara functors, introducing the cotangent complex and its various properties, and producing an analogue of the fundamental spectral sequence. Note: This thesis is reposted with a correction that appears at the end of chapter 3. Namely, we make an additional assumption that a map be a cofibration in order to generate the transitivity long exact sequence. This change influences chapter 4 and when we can generate the fundamental spectral sequence.

math.AT↗

arXiv2024

On the Differential Privacy and Interactivity of Privacy Sandbox Reports

The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities as part of the effort around limiting third-party cookies. In particular, the Private Aggregation API (PAA) and the Attribution Reporting API (ARA) can be used for ad measurement while providing different guardrails for safeguarding user privacy, including a framework for satisfying differential privacy (DP). In this work, we provide an abstract model for analyzing the privacy of these APIs and show that they satisfy a formal DP guarantee under certain assumptions. Our analysis handles the case where both the queries and database can change interactively based on previous responses from the API.

cs.CR↗

arXiv2024

Balls-and-Bins Sampling for DP-SGD

We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-SGD implementations, privacy accounting algorithms have typically assumed that Poisson subsampling is used instead. Recent work by Chua et al. (ICML 2024), however, pointed out that shuffling based DP-SGD can have a much larger privacy cost in practical regimes of parameters. In this work we show that the Balls-and-Bins sampling achieves the "best-of-both" samplers, namely, the implementation of Balls-and-Bins sampling is similar to that of Shuffling and models trained using DP-SGD with Balls-and-Bins sampling achieve utility comparable to those trained using DP-SGD with Shuffling at the same noise multiplier, and yet, Balls-and-Bins sampling enjoys similar-or-better privacy amplification as compared to Poisson subsampling in practical regimes.

cs.LG↗

arXiv2023

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

We propose a new family of label randomizers for training regression models under the constraint of label differential privacy (DP). In particular, we leverage the trade-offs between bias and variance to construct better label randomizers depending on a privately estimated prior distribution over the labels. We demonstrate that these randomizers achieve state-of-the-art privacy-utility trade-offs on several datasets, highlighting the importance of reducing bias when training neural networks with label DP. We also provide theoretical results shedding light on the structural properties of the optimal unbiased randomizers.

cs.LG↗

arXiv2023

Regression with Label Differential Privacy

We study the task of training regression models with the guarantee of label differential privacy (DP). Based on a global prior distribution on label values, which could be obtained privately, we derive a label DP randomization mechanism that is optimal under a given regression loss function. We prove that the optimal mechanism takes the form of a "randomized response on bins", and propose an efficient algorithm for finding the optimal bin values. We carry out a thorough experimental evaluation on several datasets demonstrating the efficacy of our algorithm.

cs.LG↗

arXiv2014

Affine extractors over large fields with exponential error

We describe a construction of explicit affine extractors over large finite fields with exponentially small error and linear output length. Our construction relies on a deep theorem of Deligne giving tight estimates for exponential sums over smooth varieties in high dimensions.

cs.CC↗