mlsanityData to 7 Oct 2026

Data-driven Optimal Cost Selection for Distributionally Robust Optimization

arXiv 1705.07152 ↗First posted 19 May 2017stat.MLcited by 15

Not on the map. Why?

Abstract (arXiv)

Recently, (Blanchet, Kang, and Murhy 2016, and Blanchet, and Kang 2017) showed that several machine learning algorithms, such as square-root Lasso, Support Vector Machines, and regularized logistic regression, among many others, can be represented exactly as distributionally robust optimization (DRO) problems. The distributional uncertainty is defined as a neighborhood centered at the empirical distribution. We propose a methodology which learns such neighborhood in a natural data-driven way. We show rigorously that our framework encompasses adaptive regularization as a particular case. Moreover, we demonstrate empirically that our proposed methodology is able to improve upon a wide range of popular machine learning estimators.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 2; 2023: 2; 2024: 1; 2025: 4.

15 papers.

Sort:

By area:

  1. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  2. 2021Towards a Theoretical Framework of Out-of-Distribution Generalizationcited by 94
  3. 2021Distributionally Robust Learningcited by 44
  4. 2021Statistical Analysis of Wasserstein Distributionally Robust Estimatorscited by 27
  5. 2021Distributionally Robust Semi-Supervised Learning Over Graphscited by 9
  6. 2023Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implicationscited by 5
  7. 2025DRO: A Python Library for Distributionally Robust Optimization in Machine Learningcited by 5
  8. 2021Human Imperceptible Attacks and Applications to Improve Fairnesscited by 3
  9. 2022Wasserstein Distributionally Robust Optimization with Wasserstein Barycenterscited by 3
  10. 2024LLM Embeddings Improve Test-time Adaptation to Tabular Y|X-Shiftscited by 3
  11. 2023Dr. FERMI: A Stochastic Distributionally Robust Fair Empirical Risk Minimization Frameworkcited by 1
  12. 2022Robust, Deep, and Reinforcement Learning for Management of Communication and Power Networkscited by 0
3 more
  1. 2025Mixed-feature Logistic Regression Robust to Distribution Shiftscited by 0
  2. 2025Data Heterogeneity Modeling for Trustworthy Machine Learningcited by 0
  3. 2025Data Curation Matters: Model Collapse and Spurious Shift Performance Prediction from Training on Uncurated Text Embeddingscited by 0