mlsanityData to 7 Oct 2026

When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guarantee

arXiv 2203.00176 ↗First posted 1 Mar 2022cs.LG math.OC stat.MLcited by 29

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose systematic and efficient gradient-based methods for both one-way and two-way partial AUC (pAUC) maximization that are applicable to deep learning. We propose new formulations of pAUC surrogate objectives by using the distributionally robust optimization (DRO) to define the loss for each individual positive data. We consider two formulations of DRO, one of which is based on conditional-value-at-risk (CVaR) that yields a non-smooth but exact estimator for pAUC, and another one is based on a KL divergence regularized DRO that yields an inexact but smooth (soft) estimator for pAUC. For both one-way and two-way pAUC maximization, we propose two algorithms and prove their convergence for optimizing their two formulations, respectively. Experiments demonstrate the effectiveness of the proposed algorithms for pAUC maximization for deep learning on various datasets.

Key facts. Cited by 29 papers in the map (data through 7 Oct 2026). Builds on 18 of its 43 references that are in the map. First posted on arXiv 1 Mar 2022.

Builds on

18 of 43 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  4. 2020Large-Scale Methods for Distributionally Robust Optimizationcited by 179
  5. 2020A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Contextcited by 146
  6. 2019Stochastic AUC Maximization with Deep Neural Networkscited by 61
  7. 2016Efficiency of minimizing compositions of convex functions and smooth mapscited by 59
  8. 2020Advanced Graph and Sequence Neural Networks for Molecular Property Prediction and Drug Discoverycited by 46
  9. 2018Stochastic subgradient method converges at the rate O(k-1/4) on weakly convex functionscited by 31
  10. 2022Finite-Sum Coupled Compositional Stochastic Optimization: Theory and Applicationscited by 27
  11. 2020Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Ratescited by 25
  12. 2014Online and Stochastic Gradient Methods for Non-decomposable Loss Functionscited by 21
6 more
  1. 2021Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexitycited by 21
  2. 2016Support Vector Algorithms for Optimizing the Partial Area Under the ROC Curvecited by 12
  3. 2015Two-Way Partial AUC and Its Propertiescited by 11
  4. 2014Top Rank Optimization in Linear Timecited by 9
  5. 2018Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutionscited by 9
  6. 2018Partial AUC Maximization via Nonlinear Scoring Functionscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 7; 2024: 4; 2025: 7; 2026: 5.

29 papers.

Sort:

  1. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  2. 2023On the Theories Behind Hard Negative Sampling for Recommendationcited by 18
  3. 2022Large-scale Optimization of Partial AUC in a Range of False Positive Ratescited by 15
  4. 2023LibAUC: A Deep Learning Library for X-Risk Optimizationcited by 15
  5. 2022Multi-block Min-max Bilevel Optimization with Applications in Multi-task Deep AUC Maximizationcited by 11
  6. 2023Weakly Supervised AUC Optimization: A Unified Partial AUC Approachcited by 11
  7. 2022FeDXL: Provable Federated Learning for Deep X-Risk Optimizationcited by 10
  8. 2023Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimizationcited by 10
  9. 2024Lower-Left Partial AUC: An Effective and Efficient Optimization Metric for Recommendationcited by 9
  10. 2024Improved Diversity-Promoting Collaborative Metric Learning for Recommendationcited by 9
  11. 2022Algorithmic Foundations of Empirical X-risk Minimizationcited by 7
  12. 2022Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithmcited by 5
17 more
  1. 2024Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functionscited by 4
  2. 2023DRAUC: An Instance-wise Distributionally Robust AUC Optimization Frameworkcited by 3
  3. 2023A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimizationcited by 3
  4. 2024Communication-Efficient Federated Group Distributionally Robust Optimizationcited by 3
  5. 2025Nested Stochastic Algorithm for Generalized Sinkhorn distance-Regularized Distributionally Robust Optimizationcited by 3
  6. 2025DACTYL: Diverse Adversarial Corpus of Texts Yielded from Large Language Modelscited by 3
  7. 2025Stochastic Primal-Dual Double Block-Coordinate for Two-way Partial AUC Maximizationcited by 1
  8. 2026Talos: Optimizing Top-K Accuracy in Recommender Systemscited by 1
  9. 2026A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimizationcited by 1
  10. 2023AUC Optimization from Multiple Unlabeled Datasetscited by 0
  11. 2025Towards a Trustworthy Anomaly Detection for Critical Applications through Approximated Partial AUC Losscited by 0
  12. 2025Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimizationcited by 0
  13. 2025FairPOT: Balancing AUC Performance and Fairness with Proportional Optimal Transportcited by 0
  14. 2025Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulationscited by 0
  15. 2026Memory-Efficient Continual Learning with CLIP Modelscited by 0
  16. 2026Team DACTYL at PAN 2026: Bayesian Data Mixing and Empirical X-risk Minimization for AI-text Detectioncited by 0
  17. 2026P-SRM: Selective Recovery of Rejected Predictions in Visual Trackingcited by 0