arXiv research

Private PGB boosts synthetic data quality using GANs and privacy techniques.

Optimizes sparse fine-tuning for privacy in neural networks.

Fixed-parameter tractability of private synthetic data generation

Differentially private weighted sampling improves privacy while maintaining utility.

Differentially private method for estimating individualized treatment rules.

Financial forecasting is challenging and attractive in machine learning. There are many classic solutions, as well as many deep learning based methods, proposed to deal with it yielding encouraging performance. Stock time series forecasting is the most representative problem in financial forecasting. Due to the strong …

Improved locally private sparse estimation with multiple samples per user.

New methods reduce bias in synthetic data for machine learning.

Private method measures nonlinear correlations between data hosted across two entities.

We design a new algorithm for the Euclidean $k$-means problem that operates in the local model of differential privacy. Unlike in the non-private literature, differentially private algorithms for the $k$-means objective incur both additive and multiplicative errors. Our algorithm significantly reduces the additive erro…

This paper relaxes the common prior assumption in the public and private information game of Morris and Shin (2000, 2004). For the generalized game, where the agent's prior expectations are heterogenous, it derives a sharp condition for the emergence of unique/multiple equilibria. This condition indicates that unique e…

Transform non-private e-values into differentially private ones.

Paper proposes a privacy-preserving method to control false discoveries.

We present a provably optimal differentially private algorithm for the stochastic multi-arm bandit problem, as opposed to the private analogue of the UCB-algorithm [Mishra and Thakurta, 2015; Tossou and Dimitrakakis, 2016] which doesn't meet the recently discovered lower-bound of $Ω\left(\frac{K\log(T)}ε \right)$ [Shar…

New framework provides privacy guarantees for practical federated learning.

Private statistical inference methods improve confidence interval lengths.

Differentially private hyperparameter tuning improves privacy in machine learning.

Private algorithms adapt from public to private domains with minimal labeled data.

DiPriMe forests use private medians to create balanced tree splits for privacy-protected data.

Improved ADMM for convex distributed learning with differential privacy.

Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks. Many existing methods resort to the stochastic gradient descent algorithm and apply a pre-defined sensitivity to th…

EIGAN learns private representations without centralized data, outperforming state-of-the-art.

Efficient FPGA virtualization for deep learning reduces user isolation and overhead.

New method for private linear regression under privacy constraints, achieving optimal rates.

Private mean estimation with multiple samples requires a certain number of people to maintain privacy.

A framework for private causal effect estimation without structural assumptions.

Differentially private random block coordinate descent improves utility in machine learning.

SPLICE method disentangles shared and private latent variables from multi-view data.

Private online FDR control for adaptive testing under differential privacy.

Improved differentially private deep learning with group-wise clipping techniques.

Efficient private matrix analysis algorithms for recent variants.

I studied what role the US stock markets and money markets have possibly played in the Gross Private Domestic Investment (GPDI) of the United States from the year 1959 to the year 2001, Gross Private Domestic Investment refers to the total amount of investment spending by businesses and firms located within the borders…

Many applications of machine learning, such as human health research, involve processing private or sensitive information. Privacy concerns may impose significant hurdles to collaboration in scenarios where there are multiple sites holding data and the goal is to estimate properties jointly across all datasets. Differe…

Privacy-preserving machine learning methods add randomness, leading to varying predictions.

Develops a simple method for creating private confidence intervals.

A key factor in developing high performing machine learning models is the availability of sufficiently large datasets. This work is motivated by applications arising in Software as a Service (SaaS) companies where there exist numerous similar yet disjoint datasets from multiple client companies. To overcome the challen…

We introduce a new class of context dependent, incomplete information games to serve as structured prediction models for settings with significant strategic interactions. Our games map the input context to outcomes by first condensing the input into private player types that specify the utilities, weighted interactions…

New DP bootstrap method for statistical inference with improved privacy and accuracy.

A novel Bayesian framework for private linear regression with MCMC.

We investigate the problem of nodes clustering under privacy constraints when representing a dataset as a graph. Our contribution is threefold. First we formally define the concept of differential privacy for structured databases such as graphs, and give an alternative definition based on a new neighborhood notion betw…

The use of collaborative and decentralized machine learning techniques such as federated learning have the potential to enable the development and deployment of clinical risk predictions models in low-resource settings without requiring sensitive data be shared or stored in a central repository. This process necessitat…

Due to massive amounts of data distributed across multiple locations, distributed machine learning has attracted a lot of research interests. Alternating Direction Method of Multipliers (ADMM) is a powerful method of designing distributed machine learning algorithm, whereby each agent computes over local datasets and e…

New method for uncertainty quantification in private SGD.

DPDMs use DP-SGD to generate private synthetic data.

New algorithms for private generalized linear contextual bandits.

We provide the first differentially private algorithms for controlling the false discovery rate (FDR) in multiple hypothesis testing, with essentially no loss in power under certain conditions. Our general approach is to adapt a well-known variant of the Benjamini-Hochberg procedure (BHq), making each step differential…

Framework evaluates privacy cost of non-private pre-processing in DP pipelines.

Asynchronous algorithms reduce privacy costs in distributed machine learning.