mlsanityData to 7 Oct 2026

Multiple Greedy Quasi-Newton Methods for Saddle Point Problems

arXiv 2408.00241 ↗First posted 1 Aug 2024cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

This paper introduces the Multiple Greedy Quasi-Newton (MGSR1-SP) method, a novel approach to solving strongly-convex-strongly-concave (SCSC) saddle point problems. Our method enhances the approximation of the squared indefinite Hessian matrix inherent in these problems, significantly improving both stability and efficiency through iterative greedy updates. We provide a thorough theoretical analysis of MGSR1-SP, demonstrating its linear-quadratic convergence rate. Numerical experiments conducted on AUC maximization and adversarial debiasing problems, compared with state-of-the-art algorithms, underscore our method's enhanced convergence rate. These results affirm the potential of MGSR1-SP to improve performance across a broad spectrum of machine learning applications where efficient and accurate Hessian approximations are crucial.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 62 references that are in the map. First posted on arXiv 1 Aug 2024.

Builds on

33 of 62 references.

References · 33

  1. 2022Generative Adversarial Networkscited by 5,603
  2. 2017Minimax Regret Bounds for Reinforcement Learningcited by 500
  3. 2017Training GANs with Optimismcited by 217
  4. 2019Model-Based Reinforcement Learning with a Generative Model is Minimax Optimalcited by 124
  5. 2019Reducing Noise in GAN Training with Variance Reduced Extragradientcited by 61
  6. 2016Stochastic Variance Reduction Methods for Saddle-Point Problemscited by 57
  7. 2022Nearly Minimax Optimal Reinforcement Learning for Linear Markov Decision Processescited by 57
  8. 2021Stochastic Variance Reduction for Variational Inequality Methodscited by 46
  9. 2020Greedy Quasi-Newton Methods with Explicit Superlinear Convergencecited by 21
  10. 2020Non-asymptotic Superlinear Convergence of Standard Quasi-Newton Methodscited by 16
  11. 2020Higher-order methods for convex-concave min-max optimization and monotone variational inequalitiescited by 16
  12. 2022Minimax AUC Fairness: Efficient Algorithm with Provable Convergencecited by 16
21 more
  1. 2020New Results on Superlinear Convergence of Classical Quasi-Newton Methodscited by 15
  2. 2021Near Optimal Stochastic Algorithms for Finite-Sum Unbalanced Convex-Concave Minimax Optimizationcited by 15
  3. 2022Generalized Optimistic Methods for Convex-Concave Saddle Point Problemscited by 15
  4. 2020Rates of superlinear convergence for classical quasi-Newton methodscited by 13
  5. 2021On Accelerated Methods for Saddle-Point Problems with Composite Structurecited by 13
  6. 2024Efficient Algorithms for Empirical Group Distributionally Robust Optimization and Beyondcited by 11
  7. 2021Quasi-Newton Methods for Saddle Point Problems and Beyondcited by 10
  8. 2022Optimal Methods for Higher-Order Smooth Monotone Variational Inequalitiescited by 9
  9. 2024Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Modelcited by 7
  10. 2019A Stochastic Proximal Point Algorithm for Saddle-Point Problemscited by 6
  11. 2022Universal Tensor Methods for Monotone Variational Inequalitiescited by 6
  12. 2021Explicit Convergence Rates of Greedy and Random Quasi-Newton Methodscited by 5
  13. 2022Perseus: A Simple and Optimal High-Order Method for Variational Inequalitiescited by 5
  14. 2018A Distributed Quasi-Newton Algorithm for Empirical Risk Minimization with Nonsmooth Regularizationcited by 4
  15. 2022Fairness-aware Regression Robust to Adversarial Attackscited by 4
  16. 2021Explicit Superlinear Convergence Rates of The SR1 Algorithmcited by 3
  17. 2023A structured L-BFGS method and its application to inverse problemscited by 2
  18. 2019An implicit gradient-descent procedure for minimax problemscited by 1
  19. 2023Symmetric Rank-k Methodscited by 1
  20. 2023Distributed Adaptive Greedy Quasi-Newton Methods with Explicit Non-asymptotic Convergence Boundscited by 1
  21. 2024Robust Solutions of Nonlinear Least Squares Problems via Min-max Optimizationcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 0; 2026: 1.

3 papers.

  1. 2024Adaptive Self-Supervised Learning Strategies for Dynamic On-Device LLM Personalizationcited by 5
  2. 2024Electroencephalogram Emotion Recognition via AUC Maximizationcited by 2
  3. 2026Structural shifts in institutional participation and collaboration within the AI arXiv preprint research ecosystemcited by 0