arXiv research

New privacy mechanism for user-level discrete distributions with reduced penalty.

Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…

Develops a privacy-preserving algorithm for sparse robust regression.

Cluster-DP improves differential privacy in randomized experiments by clustering data.

We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. S…

This paper enhances privacy-preserving randomized power method for large datasets.

Following the publication of an attack on genome-wide association studies (GWAS) data proposed by Homer et al., considerable attention has been given to developing methods for releasing GWAS data in a privacy-preserving way. Here, we develop an end-to-end differentially private method for solving regression problems wi…

We consider the decentralized exploration problem: a set of players collaborate to identify the best arm by asynchronously interacting with the same stochastic environment. The objective is to insure privacy in the best arm identification problem between asynchronous, collaborative, and thrifty players. In the context …

Privacy is a major issue in learning from distributed data. Recently the cryptographic literature has provided several tools for this task. However, these tools either reduce the quality/accuracy of the learning algorithm---e.g., by adding noise---or they incur a high performance penalty and/or involve trusting externa…

Generative adversarial networks create synthetic insurance datasets from confidential originals.

Proposes a game-theoretic framework for ML trust regulation.

A method for sharing synthetic data without revealing actual data or model parameters.

We tackle the problem of Federated Learning in the non i.i.d. case, in which local models drift apart, inhibiting learning. Building on an analogy with Lifelong Learning, we adapt a solution for catastrophic forgetting to Federated Learning. We add a penalty term to the loss function, compelling all local models to con…

This work generates synthetic EHRs with privacy guarantees for machine learning tasks.

Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain reg…

One-bit measurements widely exist in the real world, and they can be used to recover sparse signals. This task is known as the problem of learning halfspaces in learning theory and one-bit compressive sensing (1bit-CS) in signal processing. In this paper, we propose novel algorithms based on both convex and nonconvex s…

The paper studies robust risk measures with linear penalties under uncertain distributions.

The use of machine-learning in neuroimaging offers new perspectives in early diagnosis and prognosis of brain diseases. Although such multivariate methods can capture complex relationships in the data, traditional approaches provide irregular (l2 penalty) or scattered (l1 penalty) predictive pattern with a very limited…

Improves privacy amplification by shuffling for differential privacy.

Proposes a privacy-preserving recommendation system using matrix factorization and differential privacy.

This work optimizes mean estimation under varying privacy constraints.

Improves privacy guarantees by analyzing randomness in privacy-preserving mechanisms.

The paper analyzes and proposes methods for privately sharing individual privacy losses using per-instance differential privacy.

This work optimizes mean estimation under varying user privacy demands.

A new privacy accountant for Gaussian differential privacy measures individual privacy losses.

Paper simplifies DP composition for adaptive privacy budgets, enabling better privacy and accuracy in deep learning.

New sparse penalty improves biclustering for gene expression data.

New approach avoids excess empirical risk in domain generalization.

We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted types of penalties of this kind as motivating examples: (1) the general overlappin…

This paper bounds min-entropy leakage for Blowfish privacy using graph symmetries.

A popular heuristic for improved performance in Generative adversarial networks (GANs) is to use some form of gradient penalty on the discriminator. This gradient penalty was originally motivated by a Wasserstein distance formulation. However, the use of gradient penalty in other GAN formulations is not well motivated.…

New federated $f$-differential privacy for collaborative learning.

Differential privacy is a statistical concept that can be explained through hypothesis testing.

Curvature penalties improve interpretability of KANs without sacrificing accuracy.

New method reduces bias in sparse Bayesian learning.

A new method for tighter privacy loss accounting in adaptive analyses.

Paper tackles federated learning with privacy, enhancing target data analysis.

Unified framework for subsampling mechanisms with tighter privacy guarantees.

We consider a one-period Kyle (1985) framework where the insider can be subject to a penalty if she trades. We establish existence and uniqueness of equilibrium for virtually any penalty function when noise is uniform. In equilibrium, the demand of the insider and the price functions are in general non-linear and remai…

New findings show privacy affects generalization error in a non-monotonic way.

New nonconvex penalty smooths at origin for deep learning.

New privacy framework tailored to specific data distributions.

Addresses theoretical and practical aspects of Gaussian differential privacy.

We study the problem of learning high dimensional regression models regularized by a structured-sparsity-inducing penalty that encodes prior structural information on either input or output sides. We consider two widely adopted types of such penalties as our motivating examples: 1) overlapping group lasso penalty, base…

New filters match advanced composition for adaptive privacy, with practical constants.

Deep learning models are often trained on datasets that contain sensitive information such as individuals' shopping transactions, personal contacts, and medical records. An increasingly important line of work therefore has sought to train neural networks subject to privacy constraints that are specified by differential…

Wasserstein GAN(WGAN) is a model that minimizes the Wasserstein distance between a data distribution and sample distribution. Recent studies have proposed stabilizing the training process for the WGAN and implementing the Lipschitz constraint. In this study, we prove the local stability of optimizing the simple gradien…

Multi-group learners suffer a penalty in transductive learning.