Research map / Optimization / Nonconvex and smooth optimization
Acceleration through Optimistic No-Regret Dynamics
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 |
|---|---|---|---|
| Use OptimisticFTL with weighted regret dynamics instead of FollowTheLeader (ablation) | Fenchel-game optimization dynamics · Smooth convex optimization | optimization error: O(1/T) -> O(1/T^2) | Helped |
| Use OptimisticFTL with BeTheRegularizedLeader and exponentially growing total weights | Fenchel-game optimization dynamics · Strongly convex and smooth optimization | optimization error: O(exp(-\frac{T}{\sqrt{\kappa}})) | Helped |
| Use OptimisticFTL with proximal MirrorDescent updates | Accelerated Proximal Method · Composite convex optimization | optimization error: O(1/T^2) | Helped |
Closest papers by meaning
- Doubly Optimal No-Regret Learning in Monotone Games (ICML 2023 · similarity 0.92)
- On Last-Iterate Convergence Beyond Zero-Sum Games (ICML 2022 · similarity 0.92)
- Optimism Without Regularization: Constant Regret in Zero-Sum Games (NeurIPS 2025 · similarity 0.92)
- Near-Optimal No-Regret Learning Dynamics for General Convex Games (NeurIPS 2022 · similarity 0.91)
- Optimistic Mirror Descent Either Converges to Nash or to Strong Coarse Correlated Equilibria in Bimatrix Games (NeurIPS 2022 · similarity 0.91)
- Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms (NeurIPS 2024 · similarity 0.90)
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.