Research map / Optimization / Nonconvex and smooth optimization
Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train with a min-max objective instead of minimizing average category loss | CNN fair classifier · Fashion-MNIST, worst-case category test count, gradient descent | correctly classified samples: 658.74 -> 750.04 | Helped |
| Add regularization to the inner maximization (ablation) | MinMax fair classifier · Fashion-MNIST, worst-case category test count, gradient descent | correctly classified samples: 750.04 -> 755.66 | Helped |
| Add regularization to the inner maximization (ablation) | MinMax fair classifier · Fashion-MNIST, worst-case category test count, Adam mini-batch | correctly classified samples: 711.64 -> 734.34 | Helped |
| Replace average-loss training with min-max training | CNN fair classifier · Fashion-MNIST, T-shirt/top test count, gradient descent | correctly classified samples: 850.72 -> 774.14 | Hurt |
| Use the proposed robust min-max formulation | Robust neural network training · Adversarial test accuracy, FGSM L∞ ε=0.2 | accuracy: 96.19% -> 97.04% | Helped |
| Use the proposed robust min-max formulation | Robust neural network training · Adversarial test accuracy, PGD^40 L∞ ε=0.4 | accuracy: 94.11% -> 94.22% | Helped |
| Use the proposed robust min-max formulation | Robust neural network training · Natural test accuracy | accuracy: 98.58% -> 98.20% | Hurt |
| Add regularization to the inner maximization (ablation) | MinMax fair classifier · Fashion-MNIST, training loss convergence | convergence smoothness | Helped |
Closest papers by meaning
- Global Convergence to Local Minmax Equilibrium in Classes of Nonconvex Zero-Sum Games (NeurIPS 2021 · similarity 0.90)
- Linear Lower Bounds and Conditioning of Differentiable Games (ICML 2020 · similarity 0.90)
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics (NeurIPS 2025 · similarity 0.88)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · similarity 0.88)
- Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis (NeurIPS 2024 · similarity 0.88)
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.