Recent advances in algorithmic high-dimensional robust statistics
I Diakonikolas, DM Kane - ar** attacks via randomized smoothing
E Rosenfeld, E Winston… - … on Machine Learning, 2020 - proceedings.mlr.press
Abstract Machine learning algorithms are known to be susceptible to data poisoning attacks,
where an adversary manipulates the training data to degrade performance of the resulting …
where an adversary manipulates the training data to degrade performance of the resulting …
Robustness implies privacy in statistical estimation
We study the relationship between adversarial robustness and differential privacy in high-
dimensional algorithmic statistics. We give the first black-box reduction from privacy to …
dimensional algorithmic statistics. We give the first black-box reduction from privacy to …
Differential privacy and robust statistics in high dimensions
We introduce a universal framework for characterizing the statistical efficiency of a statistical
estimation problem with differential privacy guarantees. Our framework, which we call High …
estimation problem with differential privacy guarantees. Our framework, which we call High …
Byzantine-robust federated learning with optimal statistical rates
We propose Byzantine-robust federated learning protocols with nearly optimal statistical
rates based on recent progress in high dimensional robust statistics. In contrast to prior work …
rates based on recent progress in high dimensional robust statistics. In contrast to prior work …
A deep neural networks based model for uninterrupted marine environment monitoring
In the last few decades, there is a massive increase in population and hence increase in
societal development. Concerning environmental change as a result of development in …
societal development. Concerning environmental change as a result of development in …
Estimation contracts for outlier-robust geometric perception
L Carlone - Foundations and Trends® in Robotics, 2023 - nowpublishers.com
Outlier-robust estimation is a fundamental problem and has been extensively investigated
by statisticians and practitioners. The last few years have seen a convergence across …
by statisticians and practitioners. The last few years have seen a convergence across …
Robust and differentially private mean estimation
In statistical learning and analysis from shared data, which is increasingly widely adopted in
platforms such as federated learning and meta-learning, there are two major concerns …
platforms such as federated learning and meta-learning, there are two major concerns …