Improves privacy amplification by shuffling for differential privacy.
problem Enhancing privacy guarantees in systems with anonymous data contributions.
method Theoretical and numerical analysis of Rényi differential privacy parameters and privacy amplification by shuffling.
result First asymptotically optimal analysis of Rényi differential privacy parameters for shuffled outputs.
Simpler, faster algorithm for uniformity testing in the shuffle model.
problem Testing uniformity of data in the shuffle model with privacy constraints.
method Simplified analysis and use of privacy amplification via shuffling.
result An algorithm with the same guarantees but simpler and more streamlined.
BUDS balances privacy and utility by shuffling data, achieving strong privacy with minimal loss.
problem Balancing privacy and utility in crowd-sourced statistical databases.
method One-hot encoding, iterative shuffling, loss estimation, risk minimization.
result Achieves ε = 0.02 ε= 0.02 ε = 0.02 for privacy, maintaining a privacy bound of ε = l n [ t / ( ( n 1 − 1 ) S ) ] ε= ln [t/((n_1 - 1)^S)] ε = l n [ t / (( n 1 − 1 ) S )] . A new Gaussian mechanism for differential privacy in the shuffle model is introduced.
problem Improving differential privacy in distributed learning environments.
method Characterization and upper-bounding of Rényi differential privacy (RDP) for the shuffle Gaussian mechanism.
result The shuffle Gaussian mechanism provides improved privacy guarantees compared to existing methods.
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…
Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.
problem Enhancing privacy in systems where data is contributed anonymously.
method Developed a new approach to random shuffling that amplifies differential privacy guarantees.
result Achieved asymptotically optimal privacy amplification with nearly optimal dependence in ε.
Paper proves privacy guarantees for shuffled and online PNSGD, reducing noise over time.
problem Privacy amplification in shuffled and online PNSGD settings.
method Iterative analysis of PNSGD with hidden updates, proving privacy guarantees for shuffled and online settings.
result Privacy guarantees for shuffled and online PNSGD with reduced noise over time.
Balls-and-Bins sampling improves DP-SGD privacy and utility.
problem Improving privacy and utility in DP-SGD implementations.
method Introducing Balls-and-Bins sampling as an alternative to shuffling in DP-SGD.
result Balls-and-Bins sampling achieves utility comparable to shuffling while offering better privacy amplification.
Paper improves privacy bounds for shuffle model using novel numerical techniques.
problem Improving privacy guarantees in the shuffle model of differential privacy.
method Develops and evaluates numerical techniques for tighter ( ε , δ ) (\varepsilon,δ) ( ε , δ ) -differential privacy bounds. result Accurately evaluates privacy loss distribution for adaptive compositions of shufflers.
This paper improves privacy bounds for DP algorithms using f f f -DP.
problem Difficulty in analyzing randomness in DP algorithms due to mixture distributions.
method Derives a closed-form expression for trade-off functions and analyzes f f f -DP. result Enhances privacy of DP-GD with random initialization and shuffling models.
New algorithms for private generalized linear contextual bandits.
problem Private estimation and optimization for generalized linear models under differential privacy.
method Developed algorithms for stochastic and adversarial contexts under shuffle and joint differential privacy.
result Achieved private regret bounds for generalized linear models, differing from non-private rates by factors of d / ε \sqrt{d/\varepsilon} d / ε and d / ε \sqrt{d/\varepsilon} d / ε respectively. FLAME improves privacy in federated learning without trusted parties.
problem Ensuring privacy in federated learning without trusted parties.
method FLAME uses the shuffle model of differential privacy to achieve better accuracy and privacy.
result FLAME protocols improve testing accuracy by 60.7% compared to local model FL.
The paper explores privacy-preserving methods for counting unique elements in distributed settings.
problem Counting unique elements in a distributed setting while maintaining privacy.
method Analyzes and proves lower bounds for differentially private protocols in various settings.
result Achieves optimal error bounds for multi-message shuffle protocols in estimating distinct elements.
New method amplifies privacy in decentralized learning without centralized communication.
problem Privacy amplification in decentralized federated learning.
method Random check-in protocol for DP-SGD in FL.
result Privacy/accuracy trade-offs similar to subsampling/shuffling, but without server-initiated communication.
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…
New method improves FL efficiency by shuffling data, balancing privacy and accuracy.
problem Balancing privacy, communication, and accuracy in federated learning.
method Developed communication-efficient schemes for private mean estimation, combining privacy amplification and shuffled data.
result Achieved same privacy, optimization performance with lower communication cost.
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…
In recent work, Cheu et al. (Eurocrypt 2019) proposed a protocol for n n n -party real summation in the shuffle model of differential privacy with O ε , δ ( 1 ) O_{ε, δ}(1) O ε , δ ( 1 ) error and Θ ( ε n ) Θ(ε\sqrt{n}) Θ ( ε n ) one-bit messages per party. In contrast, every local model protocol for real summation must incur error Ω ( 1 / n ) Ω(1/\sqrt{n}) Ω ( 1/ n ) , and there exist …
Differential privacy is a useful tool to build machine learning models which do not release too much information about the training data. We study the Rényi differential privacy of stochastic gradient descent when each training example is sampled without replacement (also known as cyclic SGD). Cyclic SGD is typically f…
FLaPS improves scalability and privacy in federated learning.
problem No scalability and security/privacy trade-offs in federated learning.
method Clusters devices, uses differential privacy, iterative shuffling.
result Improved scalability and privacy with comparable performance.
New method shows hidden state can significantly improve differential privacy in SGD.
problem Differential privacy in SGD with hidden state.
method Proves converging privacy bounds for hidden state SGD, using privacy amplification techniques.
result Privacy bound converges exponentially fast and is smaller than composition bounds.
Differential privacy is a statistical concept that can be explained through hypothesis testing.
problem Formalizing differential privacy as a statistical concept.
method Using David Blackwell's informativeness theorem, the paper shows differential privacy can be understood through hypothesis testing.
result The definition of f f f -differential privacy provides a unified framework for analyzing privacy bounds. Sensitive statistics are often collected across sets of users, with repeated collection of reports done over time. For example, trends in users' private preferences or software usage may be monitored via such reports. We study the collection of such statistics in the local differential privacy (LDP) model, and describe…
Study phase transitions in shuffled regression problems.
problem Phase transitions in shuffled regression problems.
method Transformed permutation recovery into probabilistic graphical model, used message passing (MP) algorithm and branching random walk process.
result Characterized impact of signal-to-noise-ratio ( $\snr$ ) on permutation recovery, proposed Gaussian approximation method.
New algorithms improve prediction with expert advice under local differential privacy.
problem Predicting expert advice with privacy constraints.
method Design of two new algorithms: RW-AdaBatch and RW-Meta, leveraging limited-switching behavior and random walks.
result RW-Meta outperforms classical and central DP algorithms by 1.5-3x on predicting hospital COVID patient densities.
Develops shuffling gradient-based methods for nonconvex-concave minimax optimization.
problem Nonconvex-concave minimax optimization problems.
method Two shuffling gradient-based algorithms for nonconvex-linear and nonconvex-strongly concave settings.
result Achieves state-of-the-art oracle complexity in nonconvex optimization and best-known complexity bounds for nonconvex-strongly concave setting.
SMG combines shuffling and momentum for non-convex optimization.
problem Non-convex finite-sum optimization problems.
method Shuffling Gradient-based method with momentum.
result Established state-of-the-art convergence rates for SMG.
A new algorithm improves convergence rates for convex optimization problems.
problem Convex optimization problems with finite-sum structure.
method Nesterov Accelerated Shuffling Gradient (NASG) integrating Nesterov's acceleration with different shuffling schemes.
result Improved convergence rate of O(1/T) for unified shuffling schemes.
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 …
New shuffling methods improve convergence without Lipschitz smoothness.
problem Lack of convergence guarantees for shuffling methods under non-Lipschitz conditions.
method Revisit shuffling methods, prove convergence under general bounded variance condition.
result Matched current best-known convergence rates without Lipschitz smoothness.
A new method resolves permutation issues in shuffled linear regression for large-scale applications.
problem Estimating latent features through linear transformation with unknown permutations.
method Spectral matching method to align spectral components of measurement and feature covariances.
result Achieves accurate estimates in shuffled LS and LASSO settings with sufficient samples.
New convergence rates for shuffling gradient methods without strong convexity.
problem Theoretical gap between shuffling gradient methods' empirical success and established convergence rates.
method Proved last-iterate convergence rates for shuffling gradient methods using function value gap.
result First last-iterate convergence rates for shuffling gradient methods without strong convexity.
Optimal SGD rates achieved with shuffling, covering non-convex and convex cases.
problem Optimizing finite-sum optimization problems with shuffling strategies.
method RandomShuffle and SingleShuffle algorithms for SGD, analyzing convergence rates.
result Minimax optimal convergence rates established, generalizing to non-convex costs.
Unified analysis for shuffling-type gradient methods in optimization.
problem Optimization of finite-sum problems using shuffling strategies.
method Unified convergence analysis for various shuffling methods.
result Improved convergence rates for nonconvex problems and matching rates for convex problems.
New convergence bounds for shuffling-based SGD methods in distributed learning.
problem Analyzing the performance of shuffling-based variants of SGD in distributed learning.
method Study of minibatch and local Random Reshuffling methods, proving convergence bounds and lower bounds.
result Shuffling-based variants converge faster than with-replacement sampling methods, and the bounds are tight.
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
Proposes methods to recover labels from shuffled networks using graph averages.
problem Recovering labels from a shuffled network using graph averages.
method Cluster networks into classes, then match the new graph to cluster-averages, minimizing the graph matching objective function.
result Higher fidelity matching performance when clustering networks into different classes.
Improved shuffling gradient methods converge faster for nonsmooth convex optimization.
problem Improving convergence rates for nonsmooth convex optimization problems.
method Analysis of shuffling gradient methods, focusing on Random Reshuffle and Single Shuffle strategies.
result Shuffling gradient methods, particularly Random Reshuffle and Single Shuffle, converge faster than Proximal Gradient Descent for nonsmooth convex optimization.
Enhanced financial reward with shuffled feature CNN-DRL.
problem Improving reward in financial data using CNN-DRL.
method Applying shuffled features to financial data for CNN-DRL.
result Substantial enhancement in reward attainment.
New neural model processes 2D data with long-range dependencies efficiently.
problem Limited receptive field of convolutions for complex 2D tasks.
method Proposes Matrix Shuffle-Exchange network with O ( log n ) \mathcal{O}( \log{n}) O ( log n ) layers and O ( n 2 log n ) \mathcal{O}( n^2 \log{n}) O ( n 2 log n ) complexity. result Exceeds convolutional and graph neural network baselines in long-range dependency modeling.
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…
Power of network tests degrades when vertices are misaligned.
problem Power loss in network hypothesis testing due to vertex shuffling.
method Theoretical analysis and simulations of Frobenius norm differences in random dot product and stochastic block models.
result Shuffling vertices can significantly reduce the power of network tests.
Random shuffle method boosts HF dataset size 10-21 times.
problem Narrow dataset cardinality in HF clinical studies.
method Random shuffle method to enhance dataset size.
result Enhanced HF dataset size 10-21 times.
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…
Sampling without replacement speeds up optimization in minimax problems.
problem Optimizing minimax problems with faster convergence rates.
method Analysis of gradient descent ascent and proximal point method with two sampling strategies.
result Sampling without replacement leads to faster convergence rates in minimax optimization.
The paper analyzes the variance of different shuffling methods in stochastic gradient descent.
problem Understanding the variance of different shuffling methods in stochastic gradient descent.
method Power spectral density analysis to study the noise sequences of stochastic gradients.
result The stationary variances of iterates decrease in the order of SGD, SGD-RR, and SGD-SO.
Proof of injection from double shuffle to Kashiwara-Vergne Lie algebra.
problem Injecting double shuffle Lie algebra into Kashiwara-Vergne Lie algebra.
method Inclusion of brunnian braids group on different genus 0 surfaces, using lower central series of brunnian Lie algebras, and explicit links between maps.
result Injection of double shuffle Lie algebra into symmetric Kashiwara-Vergne Lie algebra.
New method uses exponential family priors to handle shuffled data problems.
problem Handling mismatch errors in record linkage of two data files.
method Flexible exponential family prior on the permutation group for regularization.
result The proposed method outperforms competing methods in synthetic and real data.