mlsanityData to 7 Oct 2026

An integrated perspective of robustness in regression through the lens of the bias-variance trade-off

arXiv 2407.10418 ↗First posted 15 Jul 2024stat.ME cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper presents an integrated perspective on robustness in regression. Specifically, we examine the relationship between traditional outlier-resistant robust estimation and robust optimization, which focuses on parameter estimation resistant to imaginary dataset-perturbations. While both are commonly regarded as robust methods, these concepts demonstrate a bias-variance trade-off, indicating that they follow roughly converse strategies.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 16 of its 50 references that are in the map. First posted on arXiv 15 Jul 2024.

Builds on

16 of 50 references.

References · 16

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  4. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  5. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 363
  6. 2016Variance-based regularization with convex objectivescited by 153
  7. 2021DORO: Distributional and Outlier Robust Optimizationcited by 54
  8. 2021Distributionally Robust Learningcited by 44
  9. 2022Overparameterized Linear Regression under Adversarial Attackscited by 21
  10. 2023Regularization properties of adversarially-trained linear regressioncited by 17
  11. 2019Optimistic Distributionally Robust Optimization for Nonparametric Likelihood Approximationcited by 12
  12. 2017The Trimmed Lasso: Sparsity and Robustnesscited by 7
4 more
  1. 2017Calibration of Distributionally Robust Empirical Optimization Modelscited by 6
  2. 2023Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Trainingcited by 6
  3. 2015Sparse and Robust Linear Regression: An Optimization Algorithm and Its Statistical Propertiescited by 3
  4. 2022A Greedy and Optimistic Approach to Clustering with a Specified Uncertainty of Covariatescited by 1

Built on by

Not cited yet.