Research map / Learning theory and algorithms / Submodular and game algorithms
The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium
Ian Gemp, Charlie Chen, Brian McWilliams
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use γ-EigenGame to estimate the top 1024 generalized eigenvectors | Neural network activations · Neural network activations, O(10^3) dimensions | subspace error: 0.002 | Improved |
| Use fixed-step updates with 100× more iterations and 1/10th the step size (ablation) | γ-EigenGame on ICA signal unmixing · Synthetic ICA | agreement with the exact SGEP solution: 100× more iterations; 1/10th the step size | Mixed |
| Vary minibatch size | Stochastic γ-EigenGame · ICA and CCA experiments | generalized eigenvalues | No clear effect |
Closest papers by meaning
- The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games (NeurIPS 2025 · similarity 0.86)
- Computing Game Symmetries and Equilibria That Respect Them (AAAI 2025 · similarity 0.84)
- Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games (NeurIPS 2025 · similarity 0.83)
- Local convergence of simultaneous min-max algorithms to differential equilibrium on Riemannian manifold (ICLR 2025 · similarity 0.83)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.83)
- The Complexity of Two-Team Polymatrix Games with Independent Adversaries (ICLR 2025 · similarity 0.83)
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.
