Robust Estimation via Robust Gradient Estimation

@article{Prasad2018RobustEV,
  title={Robust Estimation via Robust Gradient Estimation},
  author={A. Prasad and Arun Sai Suggala and Sivaraman Balakrishnan and Pradeep Ravikumar},
  journal={ArXiv},
  year={2018},
  volume={abs/1802.06485}
}
We provide a new computationally-efficient class of estimators for risk minimization. We show that these estimators are robust for general statistical models: in the classical Huber epsilon-contamination model and in heavy-tailed settings. Our workhorse is a novel robust variant of gradient descent, and we provide conditions under which our gradient descent variant provides accurate estimators in a general convex risk minimization problem. We provide specific consequences of our theory for… Expand
A Unified Approach to Robust Mean Estimation
A Robust Univariate Mean Estimator is All You Need
High-Dimensional Robust Mean Estimation via Gradient Descent
Robust descent using smoothed multiplicative noise
Adaptive Hard Thresholding for Near-optimal Consistent Robust Regression
High Dimensional Robust Sparse Regression
High Dimensional Robust Sparse Regression
High Dimensional Robust Sparse Regression
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 56 REFERENCES
Variance-based Regularization with Convex Objectives
Computationally Efficient Robust Estimation of Sparse Functionals
ROBUST EMPIRICAL MEAN ESTIMATORS
Statistical consistency and asymptotic normality for high-dimensional robust M-estimators
Loss Minimization and Parameter Estimation with Heavy Tails
Robust Sparse Estimation Tasks in High Dimensions
A General Decision Theory for Huber's $\epsilon$-Contamination Model
High-dimensional regression with noisy and missing data: Provable guarantees with non-convexity
Self Scaled Regularized Robust Regression
...
1
2
3
4
5
...