Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
- URL: http://arxiv.org/abs/2405.02341v1
- Date: Thu, 2 May 2024 03:48:47 GMT
- Title: Improved Communication-Privacy Trade-offs in $L_2$ Mean Estimation under Streaming Differential Privacy
- Authors: Wei-Ning Chen, Berivan Isik, Peter Kairouz, Albert No, Sewoong Oh, Zheng Xu,
- Abstract summary: Existing mean estimation schemes are usually optimized for $L_infty$ geometry and rely on random rotation or Kashin's representation to adapt to $L$ geometry.
We introduce a novel privacy accounting method for the sparsified Gaussian mechanism that incorporates the randomness inherent in sparsification into the DP.
Unlike previous approaches, our accounting algorithm directly operates in $L$ geometry, yielding MSEs that fast converge to those of the Gaussian mechanism.
- Score: 47.997934291881414
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We study $L_2$ mean estimation under central differential privacy and communication constraints, and address two key challenges: firstly, existing mean estimation schemes that simultaneously handle both constraints are usually optimized for $L_\infty$ geometry and rely on random rotation or Kashin's representation to adapt to $L_2$ geometry, resulting in suboptimal leading constants in mean square errors (MSEs); secondly, schemes achieving order-optimal communication-privacy trade-offs do not extend seamlessly to streaming differential privacy (DP) settings (e.g., tree aggregation or matrix factorization), rendering them incompatible with DP-FTRL type optimizers. In this work, we tackle these issues by introducing a novel privacy accounting method for the sparsified Gaussian mechanism that incorporates the randomness inherent in sparsification into the DP noise. Unlike previous approaches, our accounting algorithm directly operates in $L_2$ geometry, yielding MSEs that fast converge to those of the uncompressed Gaussian mechanism. Additionally, we extend the sparsification scheme to the matrix factorization framework under streaming DP and provide a precise accountant tailored for DP-FTRL type optimizers. Empirically, our method demonstrates at least a 100x improvement of compression for DP-SGD across various FL tasks.
Related papers
- Smoothed Normalization for Efficient Distributed Private Optimization [54.197255548244705]
Federated learning enables machine learning models with privacy of participants.
There is no differentially private distributed method for training, non-feedback problems.
We introduce a new distributed algorithm $alpha$-$sf NormEC$ with provable convergence guarantees.
arXiv Detail & Related papers (2025-02-19T07:10:32Z) - Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy [11.356444450240799]
existing algorithms do not achieve Strong Differential Privacy (DP) and Optimization guarantees at once.
We propose a new method called Clip21-SGD2M based on a novel combination of clipping, heavy-ball momentum, and Error Feedback.
arXiv Detail & Related papers (2025-02-17T11:16:21Z) - Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency [52.60557300927007]
We present a $textbfMA-OSMA$ algorithm to transfer the discrete submodular problem into a continuous optimization.
We also introduce a projection-free $textbfMA-OSEA$ algorithm, which effectively utilizes the KL divergence by mixing a uniform distribution.
Our algorithms significantly improve the $(frac11+c)$-approximation provided by the state-of-the-art OSG algorithm.
arXiv Detail & Related papers (2025-02-07T15:57:56Z) - MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes [57.24311218570012]
We extend the non-smooth convex theory of EF21-P (Anonymous 2024) and MARINA-P (arXiv:2402.06412) in the non-size convex setting.
We provide theoretical guarantees under constant, decreasing, and adaptive (aktypetype) steps.
arXiv Detail & Related papers (2024-12-22T16:18:34Z) - Differentially Private Zeroth-Order Methods for Scalable Large Language Model Finetuning [0.0]
differentially private (DP) fine-tuning of pretrained LLMs has been widely used to safeguarding the privacy of task-specific datasets.
Despite pushing the scalability of DP-SGD to its limit, DP-SGD-based fine-tuning methods are unfortunately limited by the inherent inefficiency of SGD.
arXiv Detail & Related papers (2024-02-12T17:24:15Z) - Differentially Private Decentralized Optimization with Relay Communication [1.2695958417031445]
We introduce a new measure: Privacy Leakage Frequency (PLF), which reveals the relationship between communication and privacy leakage of algorithms.
A novel differentially private decentralized primal--dual algorithm named DP-RECAL is proposed to take advantage of operator splitting method and relay communication mechanism to experience less PLF.
arXiv Detail & Related papers (2022-12-21T09:05:36Z) - Normalized/Clipped SGD with Perturbation for Differentially Private
Non-Convex Optimization [94.06564567766475]
DP-SGD and DP-NSGD mitigate the risk of large models memorizing sensitive training data.
We show that these two algorithms achieve similar best accuracy while DP-NSGD is comparatively easier to tune than DP-SGD.
arXiv Detail & Related papers (2022-06-27T03:45:02Z) - On Private Online Convex Optimization: Optimal Algorithms in
$\ell_p$-Geometry and High Dimensional Contextual Bandits [9.798304879986604]
We study the Differentially private (DP) convex optimization problem with streaming data sampled from a distribution and arrives sequentially.
We also consider the continual release model where parameters related to private information are updated and released upon each new data, often known as the online algorithms.
Our algorithm achieves in linear time the optimal excess risk when $1pleq 2$ and the state-of-the-art excess risk meeting the non-private lower ones when $2pleqinfty$.
arXiv Detail & Related papers (2022-06-16T12:09:47Z) - Private Stochastic Non-Convex Optimization: Adaptive Algorithms and
Tighter Generalization Bounds [72.63031036770425]
We propose differentially private (DP) algorithms for bound non-dimensional optimization.
We demonstrate two popular deep learning methods on the empirical advantages over standard gradient methods.
arXiv Detail & Related papers (2020-06-24T06:01:24Z)
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.