Efficient Privacy Loss Accounting for Subsampling and Random Allocation
Efficient Privacy Loss Accounting for Subsampling and Random Allocation
AuthorsVitaly Feldman, Moshe Shenfeld†
Efficient Privacy Loss Accounting for Subsampling and Random Allocation
AuthorsVitaly Feldman, Moshe Shenfeld†
We consider the privacy amplification properties of a sampling scheme in which a user’s data is used in k steps chosen randomly and uniformly from a sequence (or set) of t steps. This sampling scheme has been recently applied in the context of differentially private optimization (Chua et al., 2024a; Choquette-Choo et al., 2025) and communication-efficient high-dimensional private aggregation (Asi et al., 2025), where it was shown to have utility advantages over the standard Poisson sampling. Theoretical analyses of this sampling scheme (Feldman & Shenfeld, 2025; Dong et al., 2025) lead to bounds that are close to those of Poisson sampling, yet still have two significant shortcomings. First, in many practical settings, the resulting privacy parameters are not tight due to the approximation steps in the analysis. Second, the computed parameters are either the hockey stick or Renyi divergence, both of which introduce overheads when used in privacy loss accounting.
In this work, we demonstrate that the privacy loss distribution (PLD) of random allocation applied to any differentially private algorithm can be computed efficiently. When applied to the Gaussian mechanism, our results demonstrate that the privacy-utility trade-off for random allocation is at least as good as that of Poisson subsampling. In particular, random allocation is better suited for training via DP-SGD. To support these computations, our work develops new tools for general privacy loss accounting based on a notion of PLD realization. This notion allows us to extend accurate privacy loss accounting to subsampling which previously required manual noise-mechanism-specific analysis.
†The Hebrew University of Jerusalem
Privacy Amplification by Random Allocation
June 13, 2025research area Methods and Algorithms, research area Privacyconference NeurIPS
We consider the privacy amplification properties of a sampling scheme in which a user’s data is used in steps chosen randomly and uniformly from a sequence (or set) of steps. This sampling scheme has been recently applied in the context of differentially private optimization(Chua et al., 2024; Choquette-Choo et al., 2024) and is also motivated by communication-efficient high-dimensional private aggregation (Asi et al., 2025). Existing…
Individual Privacy Accounting via a Renyi Filter
November 19, 2021research area PrivacyWorkshop at NeurIPS
We consider a sequential setting in which a single dataset of individuals is used to perform adaptively-chosen analyses, while ensuring that the differential privacy loss of each participant does not exceed a pre-specified privacy budget. The standard approach to this problem relies on bounding a worst-case estimate of the privacy loss over all individuals and all possible values of their data, for every single analysis. Yet, in many scenarios…
