Related papers: Private Prediction via Shrinkage
This work provides tight upper- and lower-bounds for the problem of mean estimation under $\epsilon$-differential privacy in the local model, when the input is composed of $n$ i.i.d. drawn samples from a normal distribution with variance…
In this work we introduce an interactive variant of joint differential privacy towards handling online processes in which existing privacy definitions seem too restrictive. We study basic properties of this definition and demonstrate that…
We study the setup where each of $n$ users holds an element from a discrete set, and the goal is to count the number of distinct elements across all users, under the constraint of $(\epsilon, \delta)$-differentially privacy: - In the…
Due to statistical lower bounds on the learnability of many function classes under privacy constraints, there has been recent interest in leveraging public data to improve the performance of private learning algorithms. In this model,…
Differential privacy is a recent notion of privacy for statistical databases that provides rigorous, meaningful confidentiality guarantees, even in the presence of an attacker with access to arbitrary side information. We show that for a…
Practical and pervasive needs for robustness and privacy in algorithms have inspired the design of online adversarial and differentially private learning algorithms. The primary quantity that characterizes learnability in these settings is…
In this work we analyze the sample complexity of classification by differentially private algorithms. Differential privacy is a strong and well-studied notion of privacy introduced by Dwork et al. (2006) that ensures that the output of an…
ldp deployments are vulnerable to inference attacks as an adversary can link the noisy responses to their identity and subsequently, auxiliary information using the order of the data. An alternative model, shuffle DP, prevents this by…
We consider the problem of communication-constrained collaborative personalized mean estimation under a privacy constraint in an environment of several agents continuously receiving data according to arbitrary unknown agent-specific…
In the mobile Internet era, the recommender system has become an irreplaceable tool to help users discover useful items, and thus alleviating the information overload problem. Recent deep neural network (DNN)-based recommender system…
This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…
We study efficient mechanisms for the query release problem in differential privacy: given a workload of $m$ statistical queries, output approximate answers to the queries while satisfying the constraints of differential privacy. In…
We present a polynomial-time algorithm for online differentially private synthetic data generation. For a data stream within the hypercube $[0,1]^d$ and an infinite time horizon, we develop an online algorithm that generates a…
To meet the standard of differential privacy, noise is usually added into the original data, which inevitably deteriorates the predicting performance of subsequent learning algorithms. In this paper, motivated by the success of improving…
Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for hidden semantic discovery of text data and serves as a fundamental tool for text analysis in various applications. However, the LDA model as well as the training…
We present new differentially private algorithms for learning a large-margin halfspace. In contrast to previous algorithms, which are based on either differentially private simulations of the statistical query model or on private convex…
While differentially private synthetic data generation has been explored extensively in the literature, how to update this data in the future if the underlying private data changes is much less understood. We propose an algorithmic…
Numerical linear algebra plays an important role in computer science. In this paper, we initiate the study of performing linear algebraic tasks while preserving privacy when the data is streamed online. Our main focus is the space…
Differential privacy (DP) offers a theoretical upper bound on the potential privacy leakage of analgorithm, while empirical auditing establishes a practical lower bound. Auditing techniques exist forDP training algorithms. However machine…
Given a real-valued hypothesis class $\mathcal{H}$, we investigate under what conditions there is a differentially private algorithm which learns an optimal hypothesis from $\mathcal{H}$ given i.i.d. data. Inspired by recent results for the…