Recent advances in algorithmic high-dimensional robust statistics
I Diakonikolas, DM Kane - arXiv preprint arXiv:1911.05911, 2019 - arxiv.org
Learning in the presence of outliers is a fundamental problem in statistics. Until recently, all
known efficient unsupervised learning algorithms were very sensitive to outliers in high …
known efficient unsupervised learning algorithms were very sensitive to outliers in high …
Byzantine stochastic gradient descent
This paper studies the problem of distributed stochastic optimization in an adversarial setting
where, out of $ m $ machines which allegedly compute stochastic gradients every iteration …
where, out of $ m $ machines which allegedly compute stochastic gradients every iteration …
Sever: A robust meta-algorithm for stochastic optimization
In high dimensions, most machine learning methods are brittle to even a small fraction of
structured outliers. To address this, we introduce a new meta-algorithm that can take in a …
structured outliers. To address this, we introduce a new meta-algorithm that can take in a …
Mean estimation and regression under heavy-tailed distributions: A survey
G Lugosi, S Mendelson - Foundations of Computational Mathematics, 2019 - Springer
We survey some of the recent advances in mean estimation and regression function
estimation. In particular, we describe sub-Gaussian mean estimators for possibly heavy …
estimation. In particular, we describe sub-Gaussian mean estimators for possibly heavy …
Being robust (in high dimensions) can be practical
Robust estimation is much more challenging in high-dimensions than it is in one-dimension:
Most techniques either lead to intractable optimization problems or estimators that can …
Most techniques either lead to intractable optimization problems or estimators that can …
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 …
Statistical query lower bounds for robust estimation of high-dimensional gaussians and gaussian mixtures
I Diakonikolas, DM Kane… - 2017 IEEE 58th Annual …, 2017 - ieeexplore.ieee.org
We describe a general technique that yields the first Statistical Query lower bounds for a
range of fundamental high-dimensional learning problems involving Gaussian distributions …
range of fundamental high-dimensional learning problems involving Gaussian distributions …
Private robust estimation by stabilizing convex relaxations
P Kothari, P Manurangsi… - Conference on Learning …, 2022 - proceedings.mlr.press
We give the first polynomial time and sample (epsilon, delta)-differentially private (DP)
algorithm to estimate the mean, covariance and higher moments in the presence of a …
algorithm to estimate the mean, covariance and higher moments in the presence of a …
The limitations of adversarial training and the blind-spot attack
The adversarial training procedure proposed by Madry et al.(2018) is one of the most
effective methods to defend against adversarial examples in deep neural networks (DNNs) …
effective methods to defend against adversarial examples in deep neural networks (DNNs) …
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 …