arXiv research

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

Develops Merton's model for private companies using DDM.

Hypothesis tests are a crucial statistical tool for data mining and are the workhorse of scientific research in many fields. Here we present a differentially private analogue of the classic Wilcoxon signed-rank hypothesis test, which is used when comparing sets of paired (e.g., before-and-after) data values. We present…

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…

Efficient methods estimate bid and value distributions in auctions.

In this paper, we study the non-stationary online second price auction problem. We assume that the seller is selling the same type of items in $T$ rounds by the second price auction, and she can set the reserve price in each round. In each round, the bidders draw their private values from a joint distribution unknown t…

New algorithm learns regression models privately under growth condition.

Two private algorithms improve domain adaptation with privacy guarantees.

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…

Differentially Private algorithms often need to select the best amongst many candidate options. Classical works on this selection problem require that the candidates' goodness, measured as a real-valued score function, does not change by much when one person's data changes. In many applications such as hyperparameter o…

This paper introduces differentially private permutation tests for hypothesis testing.

Private equity deals predict public market returns with up to 70% accuracy.

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

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…

Algorithm ensures privacy while strictly adhering to constraints.

Study analyzes climate-tech investments across 14 sectors.

New analysis shows rational actors will deploy AGI despite negative social value due to catastrophic risk.

A new framework for private Bayesian tests maintains interpretability and computational efficiency.

New method for differentially private optimization with general Lipschitz conditions.

Data that is gathered adaptively --- via bandit algorithms, for example --- exhibits bias. This is true both when gathering simple numeric valued data --- the empirical means kept track of by stochastic bandit algorithms are biased downwards --- and when gathering more complicated data --- running hypothesis tests on c…

Study of public and private VC relationships in France using qualitative methods.

Trading floors need to be twice as deep as electronic markets to compete.

Framework generates private synthetic data for unlabeled mixed-type data.

Expands differential privacy mechanisms to include the Generalized Gaussian mechanism for improved private machine learning.

Paper explores how non-neural simulators can enhance DP synthetic data generation.

We extend Kyle's model to include stochastic liquidity and multiple assets.

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, $v^*$, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes…

Study differential privacy in multi-agent RL, achieving efficient and private learning.

New algorithms minimize regret in repeated auctions by estimating values and optimizing bids.

This paper proposes a joint energy and data market to handle uncertainty in energy procurement.

This paper proposes methods to compute differentially private confidence intervals for the median.

RDP-GAN improves GAN privacy by adding random noises to loss function.

A system for federated learning with private data, adding discrete Gaussian noise and secure aggregation.

Improved DP KDE with better privacy and efficiency.

Paper develops DP methods for low-rank matrix estimation with near-optimal performance.

This paper studies trade-offs in private prediction methods.

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

Improved Frank-Wolfe algorithm speeds up training of differentially private LASSO models.

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…

Traders in a market typically have widely different, private information on the return of an asset. The equilibrium price of the asset may reflect this information more accurately if the number of traders is large enough compared to the number of the states of the world that determine the return of the asset. We study …

We study the query complexity of a learner-private sequential learning problem, motivated by the privacy and security concerns due to eavesdropping that arise in practical applications such as pricing and Federated Learning. A learner tries to estimate an unknown scalar value, by sequentially querying an external datab…

LoRA and privacy: Random projections help but not always.

Study factors affecting liquidity on decentralized exchanges, introducing new metrics.

Asynchronous algorithms reduce privacy costs in distributed machine learning.

New algorithms for privately learning decision lists and halfspaces.

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

Differential privacy has emerged as a gold standard in privacy-preserving data analysis. A popular variant is local differential privacy, where the data holder is the trusted curator. A major barrier, however, towards a wider adoption of this model is that it offers a poor privacy-utility tradeoff. In this work, we add…

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