Research map / Learning theory and algorithms / Submodular and game algorithms
Fast Rates in Time-Varying Strongly Monotone Games
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
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 |
|---|---|---|---|
| Algorithm with two-layer online ensemble and strongly convex surrogate losses (TV-SMOG) instead of restart-based method | time-varying strongly monotone games (non-smooth) · distance tracking error | tracking error bound | Improved |
| Smoothness assumption with generalized RVU property and optimistic Hedge meta-learner | time-varying strongly monotone games (smooth) · distance tracking error | tracking error bound | Improved |
| Restart-based method requiring path length P_T replaced by parameter-free ensemble | non-smooth tracking · distance tracking error | tracking error bound | No clear effect |
| Experiments: TV-Smog and TV-Smog (Smooth) vs OGD, Restart, Ader on logistic regression, Cournot, zero-sum games | time-varying strongly monotone games · Figure 1 synthetic tracking error | tracking error | Improved |
Closest papers by meaning
- Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games (ICLR 2025 · similarity 0.89)
- Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback (NeurIPS 2025 · similarity 0.87)
- Accelerated Regularized Learning in Finite N-Person Games (NeurIPS 2024 · similarity 0.86)
- No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests (NeurIPS 2024 · similarity 0.84)
- Prediction-Aware Learning in Multi-Agent Systems (ICML 2025 · similarity 0.84)
- From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications (NeurIPS 2025 · similarity 0.84)
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.
