Search Results for author: Rachel Cummings

Found 21 papers, 6 papers with code

Truthful Linear Regression

no code implementations10 Jun 2015 Rachel Cummings, Stratis Ioannidis, Katrina Ligett

We consider the problem of fitting a linear model to data held by individuals who are concerned about their privacy.

regression

Adaptive Learning with Robust Generalization Guarantees

no code implementations24 Feb 2016 Rachel Cummings, Katrina Ligett, Kobbi Nissim, Aaron Roth, Zhiwei Steven Wu

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

no code implementations24 Feb 2016 Rachel Cummings, David M. Pennock, Jennifer Wortman Vaughan

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.

Differentially Private Online Submodular Optimization

no code implementations6 Jul 2018 Adrian Rivera Cardoso, Rachel Cummings

Our algorithm using bandit feedback is $\epsilon$-differentially private and achieves expected regret $\tilde{O}\left(\frac{n^{3/2}T^{3/4}}{\epsilon}\right)$.

Differentially Private Change-Point Detection

no code implementations NeurIPS 2018 Rachel Cummings, Sara Krehbiel, Yajun Mei, Rui Tuo, Wanrong Zhang

The change-point detection problem seeks to identify distributional changes at an unknown change-point k* in a stream of data.

Change Point Detection Fault Detection

Differentially Private Mixed-Type Data Generation For Unsupervised Learning

1 code implementation25 Sep 2019 Uthaipon Tantipongpipat, Chris Waites, Digvijay Boob, Amaresh Siva, Rachel Cummings

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.

Synthetic Data Generation Vocal Bursts Type Prediction

Privately detecting changes in unknown distributions

no code implementations ICML 2020 Rachel Cummings, Sara Krehbiel, Yuliia Lut, Wanrong Zhang

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.

Change Point Detection

Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning

1 code implementation6 Dec 2019 Uthaipon Tantipongpipat, Chris Waites, Digvijay Boob, Amaresh Ankit Siva, Rachel Cummings

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).

Synthetic Data Generation Vocal Bursts Type Prediction

PAPRIKA: Private Online False Discovery Rate Control

1 code implementation27 Feb 2020 Wanrong Zhang, Gautam Kamath, Rachel Cummings

In this work, we study False Discovery Rate (FDR) control in multiple hypothesis testing under the constraint of differential privacy for the sample.

Two-sample testing

Optimal Local Explainer Aggregation for Interpretable Prediction

no code implementations20 Mar 2020 Qiaomei Li, Rachel Cummings, Yonatan Mintz

In contrast to other heuristic methods, we use an integer optimization framework to combine local explainers into a near-global aggregate explainer.

Decision Making

Attribute Privacy: Framework and Mechanisms

no code implementations8 Sep 2020 Wanrong Zhang, Olga Ohrimenko, Rachel Cummings

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.

Attribute

Differentially Private Online Submodular Maximization

no code implementations24 Oct 2020 Sebastian Perez-Salazar, Rachel Cummings

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.

Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation

no code implementations25 Mar 2021 Chris Waites, Rachel Cummings

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.

Anomaly Detection Density Estimation +2

Outlier-Robust Optimal Transport: Duality, Structure, and Statistical Analysis

1 code implementation2 Nov 2021 Sloan Nietert, Rachel Cummings, Ziv Goldfeld

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.

Private Sequential Hypothesis Testing for Statisticians: Privacy, Error Rates, and Sample Size

no code implementations10 Apr 2022 Wanrong Zhang, Yajun Mei, Rachel Cummings

We also empirically validate our theoretical results on several synthetic databases, showing that our algorithms also perform well in practice.

Robust Estimation under the Wasserstein Distance

1 code implementation2 Feb 2023 Sloan Nietert, Rachel Cummings, Ziv Goldfeld

We study the problem of robust distribution estimation under the Wasserstein metric, a popular discrepancy measure between probability distributions rooted in optimal transport (OT) theory.

Differentially Private Synthetic Control

no code implementations24 Mar 2023 Saeyoung Rho, Rachel Cummings, Vishal Misra

In this work, we provide the first algorithms for differentially private synthetic control with explicit error bounds.

Causal Inference counterfactual +1

Mean Estimation with User-level Privacy under Data Heterogeneity

no code implementations28 Jul 2023 Rachel Cummings, Vitaly Feldman, Audra McMillan, Kunal Talwar

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.