Dual-Space Preconditioning for Variational Inequalities and Root-Finding Problems
Organizations: KU Leuven (STADIUS)
Abstract
This paper develops a dual-space preconditioning framework for variational inequalities and root-finding problems beyond classical cocoercivity and Lipschitz continuity assumptions. To this end, we introduce both a novel cocoercivity-type condition and a relaxed Lipschitz continuity condition, and derive convergence of deterministic and stochastic methods under these generalized conditions. For isotropic preconditioners, the resulting algorithms can be interpreted as variable-stepsize variants of classical methods, extending recent analyses based on -type growth conditions while allowing simpler proofs and larger stepsize ranges. We also show that the framework naturally handles variational inequalities through weak Minty-type arguments. Finally, we study the associated continuous-time dynamics and derive a variational and optimal control interpretation of the preconditioned flow. Overall, the results show that dual-space preconditioning provides a flexible mechanism for designing and analyzing operator methods beyond the standard Euclidean Lipschitz setting.
Figures & tables
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
| Problem | Method | Success | Median calls | ||
| PolarGame | CEG+ | – | |||
| Softclip-CEG+ | |||||
| Hyper-CEG+ | – | ||||
| Forsaken | CEG+ | – | |||
| Softclip-CEG+ | |||||
| Hyper-CEG+ | – |
| Method | Parameter | Decay | SWD | Modes | Near-mode fraction | |
| SEG † | – | |||||
| Clip-SEG | ||||||
| Softclip-SEG | ||||||
| Hyper-SEG | – |
| Method | Parameter | Decay | mFID | Class coverage | |
| SEG | – | ||||
| Clip-SEG | |||||
| Softclip-SEG | |||||
| Hyper-SEG | – |
Stochastic Optimization Convergence
Stochastic optimization convergence studies how noisy, sampled, or delayed updates approach solutions and how fast they do so.
See all 229 papers