Research map / Learning theory and algorithms / Submodular and game algorithms
Average-case Acceleration for Bilinear Games and Normal Matrices
Carles Domingo-Enrich, Fabian Pedregosa, Damien Scieur
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 the average-case optimal method instead of asymptotic worst-case optimal methods or extragradient | Bilinear games with iid standard Gaussian matrix entries · Bilinear Games | convergence | Improved |
| Use the average-case optimal method instead of the worst-case optimal method | Circular spectral distributions, including iid Gaussian matrices · Circular Distribution | convergence | Improved |
| Use the asymptotically average-case optimal method instead of gradient descent with stepsize 1/C | Normal operators with eigenvalues in a circularly symmetric disk · Circular spectral distributions | expected distance to solution: 1 - \frac{R^2}{C^2} | Improved |
Closest papers by meaning
- Convergence of Gradient Methods on Bilinear Zero-Sum Games (ICLR 2020 · similarity 0.89)
- Stochastic Hamiltonian Gradient Methods for Smooth Games (ICML 2020 · similarity 0.88)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.87)
- Accelerated Regularized Learning in Finite N-Person Games (NeurIPS 2024 · similarity 0.87)
- Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics (NeurIPS 2025 · similarity 0.87)
- Convergence of $\text{log}(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis (NeurIPS 2024 · similarity 0.87)
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.
