# A first-order method for nonconvex-nonconcave minimax problems under a local Kurdyka-Lojasiewicz condition

arXiv: https://arxiv.org/abs/2507.01932 · HTML: https://mlsanity.com/paper/2507.01932/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 37 references that are in the map.
- First posted on arXiv 2 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Lojasiewicz Condition](https://mlsanity.com/paper/1608.04636/) (2016)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [Stochastic model-based minimization of weakly convex functions](https://mlsanity.com/paper/1803.06523/) (2018)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods](https://mlsanity.com/paper/1902.08297/) (2019)
- [Distributionally Robust Optimization: A Review](https://mlsanity.com/paper/1908.05659/) (2019)
- [Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity](https://mlsanity.com/paper/2112.05604/) (2021)
- [Calculus of the exponent of Kurdyka-Lojasiewicz inequality and its applications to linear convergence of first-order methods](https://mlsanity.com/paper/1602.02915/) (2016)
- [First-order Convergence Theory for Weakly-Convex-Weakly-Concave Min-max Problems](https://mlsanity.com/paper/1810.10207/) (2018)
- [Accelerated Single-Call Methods for Constrained Min-Max Optimization](https://mlsanity.com/paper/2210.03096/) (2022)
- [Solving Nonconvex-Nonconcave Min-Max Problems exhibiting Weak Minty Solutions](https://mlsanity.com/paper/2201.12247/) (2022)
- [Splitting methods with variable metric for KL functions](https://mlsanity.com/paper/1405.1357/) (2014)
- [Distributionally Robust Optimization and Robust Statistics](https://mlsanity.com/paper/2401.14655/) (2024)
- [Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems](https://mlsanity.com/paper/2302.09831/) (2023)
- [What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?](https://mlsanity.com/paper/1902.00618/) (2019)
- [Nonsmooth Nonconvex-Nonconcave Minimax Optimization: Primal-Dual Balancing and Iteration Complexity Analysis](https://mlsanity.com/paper/2209.10825/) (2022)
- [Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization](https://mlsanity.com/paper/2212.12978/) (2022)
- [Zeroth-Order Alternating Gradient Descent Ascent Algorithms for a Class of Nonconvex-Nonconcave Minimax Problems](https://mlsanity.com/paper/2211.13668/) (2022)
- [Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization](https://mlsanity.com/paper/2303.03984/) (2023)
- [Nonsmooth optimization using Taylor-like models: error bounds, convergence, and termination criteria](https://mlsanity.com/paper/1610.03446/) (2016)
- [Convergence of Descent Optimization Algorithms under Polyak-L ojasiewicz-Kurdyka Conditions](https://mlsanity.com/paper/2407.00812/) (2024)
- [Doubly Smoothed Optimistic Gradients: A Universal Approach for Smooth Minimax Problems](https://mlsanity.com/paper/2506.07397/) (2025)

## Built on by (most cited first, 1 of 1)

- [A first-order method for constrained nonconvex-nonconcave minimax optimization](https://mlsanity.com/paper/2510.01168/) (2025)

## Abstract (arXiv)

We study a class of nonconvex-nonconcave minimax problems in which the inner maximization problem satisfies a local Kurdyka-Lojasiewicz (KL) condition that may vary with the outer minimization variable. In contrast to the global KL or Polyak-Lojasiewicz (PL) conditions commonly assumed in the literature -- which are significantly stronger and often too restrictive in practice -- this local KL condition accommodates a broader range of practical scenarios. However, it also introduces new analytical challenges. In particular, as an optimization algorithm progresses toward a stationary point of the problem, the region over which the KL condition holds may shrink, resulting in a more intricate and potentially ill-conditioned landscape. To address this challenge, we show that the associated maximal function is locally generalized H"older smooth. Leveraging this key property, we develop an inexact proximal gradient method for solving the minimax problem, where the inexact gradient of the maximal function is computed by applying a proximal gradient method to a KL-structured subproblem. Under mild assumptions, we establish complexity guarantees for computing an approximate stationary point of the minimax problem.