mlsanityData to 7 Oct 2026

Continuous-time Analysis for Variational Inequalities: An Overview and Desiderata

arXiv 2207.07105 ↗First posted 14 Jul 2022stat.ML cs.LG math.OCcited by 1

Not on the map. Why?

Abstract (arXiv)

Algorithms that solve zero-sum games, multi-objective agent objectives, or, more generally, variational inequality (VI) problems are notoriously unstable on general problems. Owing to the increasing need for solving such problems in machine learning, this instability has been highlighted in recent years as a significant research challenge. In this paper, we provide an overview of recent progress in the use of continuous-time perspectives in the analysis and design of methods targeting the broad VI problem class. Our presentation draws parallels between single-objective problems and multi-objective problems, highlighting the challenges of the latter. We also formulate various desiderata for algorithms that apply to general VIs and we argue that achieving these desiderata may profit from an understanding of the associated continuous-time dynamics.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 14 Jul 2022.

Builds on

25 of 50 references.

References · 25

  1. 2018Which Training Methods for GANs do actually Converge?cited by 672
  2. 2017Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysiscited by 242
  3. 2017Training GANs with Optimismcited by 217
  4. 2015A Differential Equation for Modeling Nesterov's Accelerated Gradient Method: Theory and Insightscited by 203
  5. 2017Cycles in adversarial regularized learningcited by 122
  6. 2018The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimizationcited by 98
  7. 2020Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimizationcited by 94
  8. 2017A Hitting Time Analysis of Stochastic Gradient Langevin Dynamicscited by 70
  9. 2018Understanding the Acceleration Phenomenon via High-Resolution Differential Equationscited by 68
  10. 2017Gradient descent GAN optimization is locally stablecited by 65
  11. 2019Reducing Noise in GAN Training with Variance Reduced Extragradientcited by 61
  12. 2020Last Iterate is Slower than Averaged Iterate in Smooth Convex-Concave Saddle Point Problemscited by 59
13 more
  1. 2020The limits of min-max optimization algorithms: convergence to spurious non-critical setscited by 50
  2. 2018On Gradient-Based Learning in Continuous Gamescited by 46
  3. 2019A Dynamical Systems Perspective on Nesterov Accelerationcited by 33
  4. 2018Local Saddle Point Optimization: A Curvature Exploitation Approachcited by 28
  5. 2020On dissipative symplectic integration with applications to gradient-based optimizationcited by 23
  6. 2019First-order optimization algorithms via inertial systems with Hessian driven dampingcited by 22
  7. 2019ODE Analysis of Stochastic Gradient Methods with Optimism and Anchoring for Minimax Problemscited by 16
  8. 2021Discretization Drift in Two-Player Gamescited by 14
  9. 2019Multi-Agent Learning in Network Zero-Sum Games is a Hamiltonian Systemcited by 13
  10. 2022Fast Optimistic Gradient Descent Ascent (OGDA) method in continuous and discrete timecited by 10
  11. 2020A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraintscited by 9
  12. 2021Last-Iterate Convergence of Saddle-Point Optimizers via High-Resolution Differential Equationscited by 8
  13. 2020An O(sr)-Resolution ODE Framework for Understanding Discrete-Time Algorithms and Applications to the Linear Convergence of Minimax Problemscited by 1

Built on by

Cited by year

Citing papers per year: 2024: 1.

1 paper.

  1. 2024SDEs for Minimax Optimizationcited by 6