Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private Algorithms

• URL: http://arxiv.org/abs/2602.12209v1
• Date: Thu, 12 Feb 2026 17:49:07 GMT
• Title: Keeping a Secret Requires a Good Memory: Space Lower-Bounds for Private Algorithms
• Authors: Alessandro Epasto, Xin Lyu, Pasin Manurangsi,
• Abstract summary: This paper introduces a novel proof technique based on a multi-player communication game.<n>We show that winning this communication game requires transmitting information proportional to the number of over-active users.<n>We show that this communication-theoretic technique generalizes to broad classes of problems, yielding lower bounds for private medians, quantiles, and max-select.
• Score: 67.94856074923571
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the computational cost of differential privacy in terms of memory efficiency. While the trade-off between accuracy and differential privacy is well-understood, the inherent cost of privacy regarding memory use remains largely unexplored. This paper establishes for the first time an unconditional space lower bound for user-level differential privacy by introducing a novel proof technique based on a multi-player communication game. Central to our approach, this game formally links the hardness of low-memory private algorithms to the necessity of ``contribution capping'' -- tracking and limiting the users who disproportionately impact the dataset. We demonstrate that winning this communication game requires transmitting information proportional to the number of over-active users, which translates directly to memory lower bounds. We apply this framework, as an example, to the fundamental problem of estimating the number of distinct elements in a stream and we prove that any private algorithm requires almost $\widetildeΩ(T^{1/3})$ space to achieve certain error rates in a promise variant of the problem. This resolves an open problem in the literature (by Jain et al. NeurIPS 2023 and Cummings et al. ICML 2025) and establishes the first exponential separation between the space complexity of private algorithms and their non-private $\widetilde{O}(1)$ counterparts for a natural statistical estimation task. Furthermore, we show that this communication-theoretic technique generalizes to broad classes of problems, yielding lower bounds for private medians, quantiles, and max-select.

Related papers

• Linear-Time User-Level DP-SCO via Robust Statistics [55.350093142673316]
  User-level differentially private convex optimization (DP-SCO) has garnered significant attention due to the importance of safeguarding user privacy in machine learning applications.<n>Current methods, such as those based on differentially private gradient descent (DP-SGD), often struggle with high noise accumulation and suboptimal utility.<n>We introduce a novel linear-time algorithm that leverages robust statistics, specifically the median and trimmed mean, to overcome these challenges.
  arXiv  Detail & Related papers  (2025-02-13T02:05:45Z)
• Optimal Private Discrete Distribution Estimation with One-bit Communication [63.413106413939836]
  We consider a private discrete distribution estimation problem with one-bit communication constraint. We characterize the first-orders of the worst-case trade-off under the one-bit communication constraint. These results demonstrate the optimal dependence of the privacy-utility trade-off under the one-bit communication constraint.
  arXiv  Detail & Related papers  (2023-10-17T05:21:19Z)
• Differentially Private Secure Multiplication: Hiding Information in the Rubble of Noise [7.110450972801578]
  We consider the problem of private distributed multi-party multiplication.<n>It is well-established that Shamir secret-sharing coding strategies can enable perfect information-theoretic privacy in distributed computation.
  arXiv  Detail & Related papers  (2023-09-28T02:13:13Z)
• Unbounded Differentially Private Quantile and Maximum Estimation [2.855485723554975]
  We show that a simple invocation of $textttAboveThreshold$ can give more accurate and robust estimates on the highest quantiles. We show that an improved analysis of $textttAboveThreshold$ can improve the privacy guarantees for the widely used Sparse Vector Technique.
  arXiv  Detail & Related papers  (2023-05-02T03:23:07Z)
• Privacy Amplification via Shuffling: Unified, Simplified, and Tightened [20.10078781197001]
  We propose a comprehensive framework for privacy amplification in both single-message and multi-message shuffle protocols. Our theoretical results demonstrate that our framework provides tighter bounds, especially for local randomizers with extremal probability design. Our bounds also result in a remarkably efficient $tildeO(n)$ algorithm that numerically amplifies privacy in less than $10$ seconds for $n=108$ users.
  arXiv  Detail & Related papers  (2023-04-11T06:27:25Z)
• On Differential Privacy and Adaptive Data Analysis with Bounded Space [76.10334958368618]
  We study the space complexity of the two related fields of differential privacy and adaptive data analysis. We show that there exists a problem P that requires exponentially more space to be solved efficiently with differential privacy. The line of work on adaptive data analysis focuses on understanding the number of samples needed for answering a sequence of adaptive queries.
  arXiv  Detail & Related papers  (2023-02-11T14:45:31Z)
• Smooth Anonymity for Sparse Graphs [69.1048938123063]
  differential privacy has emerged as the gold standard of privacy, however, when it comes to sharing sparse datasets. In this work, we consider a variation of $k$-anonymity, which we call smooth-$k$-anonymity, and design simple large-scale algorithms that efficiently provide smooth-$k$-anonymity.
  arXiv  Detail & Related papers  (2022-07-13T17:09:25Z)
• Learning with User-Level Privacy [61.62978104304273]
  We analyze algorithms to solve a range of learning tasks under user-level differential privacy constraints. Rather than guaranteeing only the privacy of individual samples, user-level DP protects a user's entire contribution. We derive an algorithm that privately answers a sequence of $K$ adaptively chosen queries with privacy cost proportional to $tau$, and apply it to solve the learning tasks we consider.
  arXiv  Detail & Related papers  (2021-02-23T18:25:13Z)
• Robust and Differentially Private Mean Estimation [40.323756738056616]
  Differential privacy has emerged as a standard requirement in a variety of applications ranging from the U.S. Census to data collected in commercial devices. An increasing number of such databases consist of data from multiple sources, not all of which can be trusted. This leaves existing private analyses vulnerable to attacks by an adversary who injects corrupted data.
  arXiv  Detail & Related papers  (2021-02-18T05:02:49Z)
• Breaking the Communication-Privacy-Accuracy Trilemma [19.399122892615573]
  Two major challenges in distributed learning are preserving the privacy of local samples and communicating them efficiently to a central server. We develop novel encoding and decoding mechanisms that simultaneously achieve optimal privacy and communication efficiency.
  arXiv  Detail & Related papers  (2020-07-22T22:43:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.