arXiv research

Power of network tests degrades when vertices are misaligned.

OmniMatch algorithm perfectly matches graphs without edge correlation.

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

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

SMG combines shuffling and momentum for non-convex optimization.

A new algorithm improves convergence rates for convex optimization problems.

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

Improves privacy amplification by shuffling for differential privacy.

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.

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…

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

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

DS-Sync improves distributed DNN training efficiency by 94% with minimal accuracy loss.

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

Unified analysis of asynchronous-SGD algorithms for distributed learning.

New convergence rates for shuffling gradient methods without strong convexity.

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

We study configuration space integral formulas for Milnor's homotopy link invariants, showing that they are in correspondence with certain linear combinations of trivalent trees. Our proof is essentially a combinatorial analysis of a certain space of trivalent "homotopy link diagrams" which corresponds to all finite ty…

Unified analysis for shuffling-type gradient methods in optimization.

New convergence bounds for shuffling-based SGD methods in 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…

Improved shuffling technique amplifies privacy guarantees for anonymous data contributions.

Improved shuffling gradient methods converge faster for nonsmooth convex optimization.

This paper presents a new method for solving systems with polynomial stiffness.

Enhanced financial reward with shuffled feature CNN-DRL.

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

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…

A new concept of Loday algebroid (and its pure algebraic version - Loday pseudoalgebra) is proposed and discussed in comparison with other similar structures present in the literature. The structure of a Loday pseudoalgebra and its natural reduction to a Lie pseudoalgebra is studied. Further, Loday algebroids are inter…

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 …

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…

Random shuffle method boosts 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.

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

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

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

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-…

A novel RNN model with shuffled hidden states.

ShuffleNet is a state-of-the-art light weight convolutional neural network architecture. Its basic operations include group, channel-wise convolution and channel shuffling. However, channel shuffling is manually designed empirically. Mathematically, shuffling is a multiplication by a permutation matrix. In this paper, …

Random Reshuffling outperforms Stochastic Gradient Descent in smooth convex optimization.

Paper improves privacy bounds for shuffle model using novel numerical techniques.

A new algorithm speeds up matrix multiplication without actual multiplication.

New algorithms for private generalized linear contextual bandits.

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

The paper explores privacy-preserving methods for counting unique elements in distributed settings.