Search Results for author:
Found 9 papers, 0 papers with code
From Robustness to Privacy and Back
Thus, we conclude that for any low-dimensional task, the optimal error rate for $\varepsilon$-differentially private estimators is essentially the same as the optimal error rate for estimators that are robust to adversarially corrupting $1/\varepsilon$ training samples.
Multitask Learning via Shared Features: Algorithms and Hardness
We investigate the computational efficiency of multitask learning of Boolean functions over the $d$-dimensional hypercube, that are related by means of a feature representation of size $k \ll d$ shared across all tasks.
Covariance-Aware Private Mean Estimation Without Private Covariance Estimation
Each of our estimators is based on a simple, general approach to designing differentially private mechanisms, but with novel technical steps to make the estimator private and sample-efficient.
PAC-Bayes, MAC-Bayes and Conditional Mutual Information: Fast rate bounds that handle general VC classes
We give a novel, unified derivation of conditional PAC-Bayesian and mutual information (MI) generalization bounds.
Differentially Private Decomposable Submodular Maximization
We extend this work by designing differentially private algorithms for both monotone and non-monotone decomposable submodular maximization under general matroid constraints, with competitive utility guarantees.
Reasoning About Generalization via Conditional Mutual Information
We provide an information-theoretic framework for studying the generalization properties of machine learning algorithms.
Private Identity Testing for High-Dimensional Distributions
In this work we present novel differentially private identity (goodness-of-fit) testers for natural and widely studied classes of multivariate product distributions: Gaussians in $\mathbb{R}^d$ with known covariance and product distributions over $\{\pm 1\}^{d}$.
Efficient Private Algorithms for Learning Large-Margin Halfspaces
We present new differentially private algorithms for learning a large-margin halfspace.
Improved Algorithms for Collaborative PAC Learning
We study a recent model of collaborative PAC learning where $k$ players with $k$ different tasks collaborate to learn a single classifier that works for all tasks.
