arXiv research

Discond-VAE separates continuous and discrete factors in data.

Private variable selection method controls FDR with simulations showing reasonable power.

Novel privatization framework for high-dimensional variable selection with differential privacy.

It is challenging for stochastic optimizations to handle large-scale sensitive data safely. Recently, Duchi et al. proposed private sampling strategy to solve privacy leakage in stochastic optimizations. However, this strategy leads to robustness degeneration, since this strategy is equal to the noise injection on each…

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

Paper introduces DP methods for high-dimensional variable selection.

We derive concentration inequalities for differentially private median and mean estimators building on the "Propose, Test, Release" (PTR) mechanism introduced by Dwork and Lei (2009). We introduce a new general version of the PTR mechanism that allows us to derive high probability error bounds for differentially privat…

Develops a high-dimensional differentially-private EM algorithm with near-optimal statistical guarantees.

New methods for private statistical inference under local differential privacy.

Study differentially private methods for learning Hawkes processes.

Proposes a privacy-preserving sign selection method for distributed systems.

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…

Develops a simple method for creating private confidence intervals.

New algorithm learns optimal policies in strategic MDPs with private types.

We tackle the problem of estimating a location parameter with differential privacy guarantees and sub-Gaussian deviations. Recent work in statistics has focused on the study of estimators that achieve sub-Gaussian type deviations even for heavy tailed data. We revisit some of these estimators through the lens of differ…

Improved locally private sparse estimation with multiple samples per user.

Study assesses the impact of Basel III reforms on Bangladeshi banks.

PACE-GGM uses Gaussian mechanism for private covariance estimation.

This research investigated the potential for improving Peer-to-Peer (P2P) credit scoring by using "private information" about communications and travels of borrowers. We found that P2P borrowers' ego networks exhibit scale-free behavior driven by underlying preferential attachment mechanisms that connect borrowers in a…

Google Trends data improves economic forecasts of private consumption.

Paper proposes a differentially private test for joint dependence among random vectors.

Differentially-private FNAS protects privacy while collaboratively searching for neural architectures.

Differentially private geodesic regression for non-Euclidean data.

New algorithm protects privacy in IVaR regression while maintaining accuracy.

Improved ADMM for convex distributed learning with differential privacy.

We provide a differentially private algorithm for hypothesis selection. Given samples from an unknown probability distribution $P$ and a set of $m$ probability distributions $\mathcal{H}$, the goal is to output, in a $\varepsilon$-differentially private manner, a distribution from $\mathcal{H}$ whose total variation di…

New algorithms achieve optimal DP convex optimization with linear time and gradient computations.

PrAda-GAN improves synthetic data generation under differential privacy.

The iterative nature of the expectation maximization (EM) algorithm presents a challenge for privacy-preserving estimation, as each iteration increases the amount of noise needed. We propose a practical private EM algorithm that overcomes this challenge using two innovations: (1) a novel moment perturbation formulation…

Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation learning and deep neural networks, and motivated by novel information theoretica…

Unsupervised learning on imbalanced data is challenging because, when given imbalanced data, current model is often dominated by the major category and ignores the categories with small amount of data. We develop a latent variable model that can cope with imbalanced data by dividing the latent space into a shared space…

DPNR preserves privacy of text representations using differential privacy.

Study human-machine interaction with private info using offline RL.

Causal inference deals with identifying which random variables "cause" or control other random variables. Recent advances on the topic of causal inference based on tools from statistical estimation and machine learning have resulted in practical algorithms for causal inference. Causal inference has the potential to hav…

Hypothesis testing is one of the most common types of data analysis and forms the backbone of scientific research in many disciplines. Analysis of variance (ANOVA) in particular is used to detect dependence between a categorical and a numerical variable. Here we show how one can carry out this hypothesis test under the…

Distributed estimation and learning with privacy preserved.

Paper develops models to forecast private equity fund cash flows.

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

This paper studies trade-offs in private prediction methods.

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

Improved linear regression with privacy and robustness guarantees.

New algorithms for privately learning decision lists and halfspaces.

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

Near-optimal private tests for simple and MLR hypotheses developed under Gaussian differential privacy.

PEARL uses AI to replicate private equity performance with liquid assets.

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…

Public pretraining improves private model training even in extreme distribution shift scenarios.

Private learning of Gaussian Mixture Models without boundedness assumptions.