mlsanityData to 7 Oct 2026

Robust Optimization for Non-Convex Objectives

arXiv 1707.01047 ↗First posted 4 Jul 2017cs.LG cs.DS stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

We consider robust optimization problems, where the goal is to optimize in the worst case over a class of objective functions. We develop a reduction from robust improper optimization to Bayesian optimization: given an oracle that returns α-approximate solutions for distributions over objectives, we compute a distribution over solutions that is α-approximate in the worst case. We show that de-randomizing this solution is NP-hard in general, but can be done for a broad class of statistical learning tasks. We apply our results to robust neural network training and submodular optimization. We evaluate our approach experimentally on corrupted character classification, and robust influence maximization in networks.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jul 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 6; 2024: 5; 2025: 5; 2026: 1.

34 papers.

Sort:

By area:

  1. 2021Stability and Generalization of Stochastic Gradient Methods for Minimax Problemscited by 35
  2. 2022Rank-based Decomposable Losses in Machine Learning: A Surveycited by 26
  3. 2022Minimax Demographic Group Fairness in Federated Learningcited by 24
  4. 2022Net benefit, calibration, threshold selection, and training objectives for algorithmic fairness in healthcarecited by 16
  5. 2023Investigating the Limitation of CLIP Models: The Worst-Performing Categoriescited by 12
  6. 2021Training Over-parameterized Models with Non-decomposable Objectivescited by 11
  7. 2021Federating for Learning Group Fair Modelscited by 9
  8. 2023A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigmcited by 9
  9. 2021Max-Min Grouped Banditscited by 7
  10. 2022Demystifying Swarm Learning: A New Paradigm of Blockchain-based Decentralized Federated Learningcited by 7
  11. 2023Best-Effort Adaptationcited by 7
  12. 2024DRoP: Distributionally Robust Data Pruningcited by 7
22 more
  1. 2022Robust Distillation for Worst-class Performancecited by 6
  2. 2021Minimax Optimization: The Case of Convex-Submodularcited by 5
  3. 2022Learning Distributionally Robust Models at Scale via Composite Optimizationcited by 5
  4. 2021Lexicographically Fair Learning: Algorithms and Generalizationcited by 4
  5. 2023REDUCR: Robust Data Downsampling Using Class Priority Reweightingcited by 3
  6. 2021Instance Specific Approximations for Submodular Maximizationcited by 2
  7. 2022Stability and Generalization of Differentially Private Minimax Problemscited by 2
  8. 2022Balancing Utility and Fairness in Submodular Maximization (Technical Report)cited by 2
  9. 2022Learned-Database Systems Securitycited by 2
  10. 2023Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimizationcited by 2
  11. 2024Taking a Moment for Distributional Robustnesscited by 1
  12. 2024Predicting Cascading Failures with a Hyperparametric Diffusion Modelcited by 1
  13. 2025Multi-Metric Adaptive Experimental Design Under a Fixed Budget with Validationcited by 1
  14. 2025Simple Optimizers for Convex Aligned Multi-Objective Optimizationcited by 1
  15. 2021Adversaries in Online Learning Revisited: with applications in Robust Optimization and Adversarial trainingcited by 0
  16. 2023Fair Graph Machine Learning under Adversarial Missingness Processescited by 0
  17. 2024Towards Sharper Risk Bounds for Minimax Problemscited by 0
  18. 2024Alpha and Prejudice: Improving α-sized Worst-case Fairness via Intrinsic Reweightingcited by 0
  19. 2025Cost-Sensitive Learning for Long-Tailed Temporal Action Segmentationcited by 0
  20. 2025Private Rate-Constrained Optimization with Applications to Fair Learningcited by 0
  21. 2025Probabilistic Safety Guarantee for Stochastic Control Systems Using Average Reward MDPscited by 0
  22. 2026Retraction-Free Optimization over the Stiefel Manifold for the LoRA Fine-Tuningcited by 0