Search Results for author:
Found 23 papers, 6 papers with code
Differential Privacy Under Class Imbalance: Methods and Empirical Insights
We consider DP variants of pre-processing methods that privately augment the original dataset to reduce the class imbalance; these include oversampling, SMOTE, and private synthetic data generation.
Thompson Sampling Itself is Differentially Private
In this work we first show that the classical Thompson sampling algorithm for multi-arm bandits is differentially private as-is, without any modification.
Mean Estimation with User-level Privacy under Data Heterogeneity
In this work we propose a simple model of heterogeneous user data that allows user data to differ in both distribution and quantity of data, and provide a method for estimating the population-level mean while preserving user-level differential privacy.
Differentially Private Synthetic Control
In this work, we provide the first algorithms for differentially private synthetic control with explicit error bounds.
Robust Estimation under the Wasserstein Distance
We prove new structural properties for POT and use them to show that MDE under a partial Wasserstein distance achieves the minimax-optimal robust estimation risk in many settings.
Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size
We also empirically validate our theoretical results on several synthetic databases, showing that our algorithms also perform well in practice.
Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis
The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy measure between probability distributions with various applications to statistics and machine learning.
Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation.
Differentially Private Online Submodular Maximization
Our algorithms contains $k$ ordered experts that learn the best marginal item to select given the items chosen her predecessors, while maintaining privacy of the functions.
Attribute Privacy: Framework and Mechanisms
We propose definitions to capture \emph{attribute privacy} in two relevant cases where global attributes may need to be protected: (1) properties of a specific dataset and (2) parameters of the underlying distribution from which dataset is sampled.
Optimal Local Explainer Aggregation for Interpretable Prediction
In contrast to other heuristic methods, we use an integer optimization framework to combine local explainers into a near-global aggregate explainer.
PAPRIKA: Private Online False Discovery Rate Control
In this work, we study False Discovery Rate (FDR) control in multiple hypothesis testing under the constraint of differential privacy for the sample.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning
We introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of Generative Adversarial Networks (GANs).
Learning Auctions with Robust Incentive Guarantees
We study the problem of learning Bayesian-optimal revenue-maximizing auctions.
Privately detecting changes in unknown distributions
Much of the prior work on change-point detection---including the only private algorithms for this problem---requires complete knowledge of the pre-change and post-change distributions.
Differentially Private Mixed-Type Data Generation For Unsupervised Learning
In this work we introduce the DP-auto-GAN framework for synthetic data generation, which combines the low dimensional representation of autoencoders with the flexibility of GANs.
Differentially Private Change-Point Detection
The change-point detection problem seeks to identify distributional changes at an unknown change-point k* in a stream of data.
Differentially Private Online Submodular Optimization
Our algorithm using bandit feedback is $\epsilon$-differentially private and achieves expected regret $\tilde{O}\left(\frac{n^{3/2}T^{3/4}}{\epsilon}\right)$.
Adaptive Learning with Robust Generalization Guarantees
We also show that perfect generalization is a strictly stronger guarantee than differential privacy, but that, nevertheless, many learning tasks can be carried out subject to the guarantees of perfect generalization.
The Possibilities and Limitations of Private Prediction Markets
We consider the design of private prediction markets, financial markets designed to elicit predictions about uncertain events without revealing too much information about market participants' actions or beliefs.
Truthful Linear Regression
We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy.
Online Learning and Profit Maximization from Revealed Preferences
We consider the problem of learning from revealed preferences in an online setting.
