mlsanityData to 7 Oct 2026

Stochastic Optimization for Spectral Risk Measures

arXiv 2212.05149 ↗First posted 10 Dec 2022stat.ML cs.LG math.OCcited by 7

Not on the map. Why?

Abstract (arXiv)

Spectral risk objectives - also called L-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task. We develop stochastic algorithms to optimize these quantities by characterizing their subdifferential and addressing challenges such as biasedness of subgradient estimates and non-smoothness of the objective. We show theoretically and experimentally that out-of-the-box approaches such as stochastic subgradient and dual averaging are hindered by bias and that our approach outperforms them.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 24 of its 72 references that are in the map. First posted on arXiv 10 Dec 2022.

Builds on

24 of 72 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  5. 2014SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectivescited by 401
  6. 2020Fast Differentiable Sorting and Rankingcited by 196
  7. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  8. 2019Wasserstein Distributionally Robust Optimization: Theory and Applications in Machine Learningcited by 169
  9. 2016Variance-based regularization with convex objectivescited by 153
  10. 2020Tilted Empirical Risk Minimizationcited by 103
  11. 2020The iWildCam 2020 Competition Datasetcited by 86
  12. 2019Fairness risk measurescited by 85
12 more
  1. 2017Learning with Average Top-k Losscited by 52
  2. 2019Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimizationcited by 51
  3. 2021Distributionally Robust Learningcited by 44
  4. 2015Variance Reduced Stochastic Gradient Descent with Neighborscited by 39
  5. 2019Adaptive Sampling for Stochastic Risk-Averse Learningcited by 39
  6. 2014Incremental Majorization-Minimization Optimization with Application to Large-Scale Machine Learningcited by 35
  7. 2020Learning Bounds for Risk-sensitive Learningcited by 33
  8. 2019A Wasserstein distance approach for concentration of empirical risk estimatescited by 18
  9. 2022Superquantiles at Work: Machine Learning Applications and Efficient Subgradient Computationcited by 10
  10. 2019Estimation of Spectral Risk Measurescited by 9
  11. 2021Spectral risk-based learning using unbounded lossescited by 8
  12. 2020First-order Optimization for Superquantile-based Supervised Learningcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 1; 2026: 2.

7 papers.

  1. 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyondcited by 11
  2. 2026OrderDP: A Theoretically Guaranteed Lossless Dynamic Data Pruning Frameworkcited by 2
  3. 2024On Calibration in Multi-Distribution Learningcited by 1
  4. 2024When fairness metrics fail: A utility-based perspective on varepsilon-fairnesscited by 0
  5. 2024SOREL: A Stochastic Algorithm for Spectral Risks Minimizationcited by 0
  6. 2025Optimizing Shortfall Risk Metric for Learning Regression Modelscited by 0
  7. 2026Convergence of empirical subgradients for optimal transport-based objectivescited by 0