arXiv research

Improves privacy amplification by shuffling for differential privacy.

Random shuffle method boosts HF dataset size 10-21 times.

Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.

This work studies differential privacy in the context of the recently proposed shuffle model. Unlike in the local model, where the server collecting privatized data from users can track back an input to a specific user, in the shuffle model users submit their privatized inputs to a server anonymously. This setup yields…

A new algorithm improves convergence rates for convex optimization problems.

Improved shuffling gradient methods converge faster for nonsmooth convex optimization.

New convergence bounds for shuffling-based SGD methods in distributed learning.

New shuffling methods improve convergence without Lipschitz smoothness.

In this paper, we propose a unified convergence analysis for a class of generic shuffling-type gradient methods for solving finite-sum optimization problems. Our analysis works with any sampling without replacement strategy and covers many known variants such as randomized reshuffling, deterministic or randomized singl…

Power of network tests degrades when vertices are misaligned.

This paper improves privacy bounds for DP algorithms using $f$-DP.

We study the performance of stochastic gradient descent (SGD) on smooth and strongly-convex finite-sum optimization problems. In contrast to the majority of existing theoretical works, which assume that individual functions are sampled with replacement, we focus here on popular but poorly-understood heuristics, which i…

The paper analyzes the variance of different shuffling methods in stochastic gradient descent.

New convergence rates for shuffling gradient methods without strong convexity.

Random Reshuffling outperforms Stochastic Gradient Descent in smooth convex optimization.

OmniMatch algorithm perfectly matches graphs without edge correlation.

Improved convergence for VIPs with SEG-RR, a variant of SEG with random reshuffling.

Sampling without replacement speeds up optimization in minimax problems.

New method amplifies privacy in decentralized learning without centralized communication.

Although the convolutional neural networks (CNNs) have become popular for various image processing and computer vision task recently, it remains a challenging problem to reduce the storage cost of the parameters for resource-limited platforms. In the previous studies, tensor decomposition (TD) has achieved promising co…

Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the contributions of individual users. Current practical protocols for secure aggregation work…

RR algorithm improves convergence rate without strong convexity assumptions.

Develops shuffling gradient-based methods for nonconvex-concave minimax optimization.

SMG combines shuffling and momentum for non-convex optimization.

A new Gaussian mechanism for differential privacy in the shuffle model is introduced.

When using stochastic gradient descent to solve large-scale machine learning problems, a common practice of data processing is to shuffle the training data, partition the data across multiple machines if needed, and then perform several epochs of training on the re-shuffled (either locally or globally) data. The above …

Simpler, faster algorithm for uniformity testing in the shuffle model.

A new method resolves permutation issues in shuffled linear regression for large-scale applications.

BUDS balances privacy and utility by shuffling data, achieving strong privacy with minimal loss.

This paper develops a path-first theory using signatures and jump lifts for self-exiting processes.

Optimal SGD rates achieved with shuffling, covering non-convex and convex cases.

Most deep learning models are based on deep neural networks with multiple layers between input and output. The parameters defining these layers are initialized using random values and are "learned" from data, typically using stochastic gradient descent based algorithms. These algorithms rely on data being randomly shuf…

Study phase transitions in shuffled regression problems.

We point out important problems with the common practice of using the best single model performance for comparing deep learning architectures, and we propose a method that corrects these flaws. Each time a model is trained, one gets a different result due to random factors in the training process, which include random …

Unified analysis of asynchronous-SGD algorithms for distributed learning.

Proposes methods to recover labels from shuffled networks using graph averages.

An exciting new development in differential privacy is the shuffled model, in which an anonymous channel enables non-interactive, differentially private protocols with error much smaller than what is possible in the local model, while relying on weaker trust assumptions than in the central model. In this paper, we stud…

The paper explores how low-degree polynomials can detect shuffled linear regression models.

FLAME improves privacy in federated learning without trusted parties.

Enhanced financial reward with shuffled feature CNN-DRL.

New neural model processes 2D data with long-range dependencies efficiently.

In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for $n$-party real summation in the shuffle model of differential privacy with $O_{ε, δ}(1)$ error and $Θ(ε\sqrt{n})$ one-bit messages per party. In contrast, every local model protocol for real summation must incur error $Ω(1/\sqrt{n})$, and there exist …

We consider the problem of inference in a linear regression model in which the relative ordering of the input features and output labels is not known. Such datasets naturally arise from experiments in which the samples are shuffled or permuted during the protocol. In this work, we propose a framework that treats the un…

Paper proves privacy guarantees for shuffled and online PNSGD, reducing noise over time.

Proof of injection from double shuffle to Kashiwara-Vergne Lie algebra.

New method uses exponential family priors to handle shuffled data problems.

Balls-and-Bins sampling improves DP-SGD privacy and utility.

Is it possible to perform linear regression on datasets whose labels are shuffled with respect to the inputs? We explore this question by proposing several estimators that recover the weights of a noisy linear model from labels that are shuffled by an unknown permutation. We show that the analog of the classical least-…