Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Sequential (quickest) change detection: Classical results and new directions
Online detection of changes in stochastic systems, referred to as sequential change
detection or quickest change detection, is an important research topic in statistics, signal …
detection or quickest change detection, is an important research topic in statistics, signal …
The structure of optimal private tests for simple hypotheses
Hypothesis testing plays a central role in statistical inference, and is used in many settings
where privacy concerns are paramount. This work answers a basic question about privately …
where privacy concerns are paramount. This work answers a basic question about privately …
A primer on private statistics
Differentially private statistical estimation has seen a flurry of developments over the last
several years. Study has been divided into two schools of thought, focusing on empirical …
several years. Study has been divided into two schools of thought, focusing on empirical …
Sequential changepoint detection via backward confidence sequences
S Shekhar, A Ramdas - International Conference on …, 2023 - proceedings.mlr.press
We present a simple reduction from sequential estimation to sequential changepoint
detection (SCD). In short, suppose we are interested in detecting changepoints in some …
detection (SCD). In short, suppose we are interested in detecting changepoints in some …
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 R^ d with …
and widely studied classes of multivariate product distributions: Gaussians in R^ d with …
Learning in volatile environments with the bayes factor surprise
Surprise-based learning allows agents to rapidly adapt to nonstationary stochastic
environments characterized by sudden changes. We show that exact Bayesian inference in …
environments characterized by sudden changes. We show that exact Bayesian inference in …
Locally private online change point detection
We study online change point detection problems under the constraint of local differential
privacy (LDP) where, in particular, the statistician does not have access to the raw data. As a …
privacy (LDP) where, in particular, the statistician does not have access to the raw data. As a …
Private high-dimensional hypothesis testing
S Narayanan - Conference on Learning Theory, 2022 - proceedings.mlr.press
We provide improved differentially private algorithms for identity testing of high-dimensional
distributions. Specifically, for $ d $-dimensional Gaussian distributions with known …
distributions. Specifically, for $ d $-dimensional Gaussian distributions with known …
Online privacy-preserving data-driven network anomaly detection
We study online privacy-preserving anomaly detection in a setting in which the data are
distributed over a network and locally sensitive to each node, and a probabilistic data model …
distributed over a network and locally sensitive to each node, and a probabilistic data model …