Research map / Bandits and online learning / Online convex optimization and games
Dynamic Thresholding and Pruning for Regret Minimization
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 |
|---|---|---|---|
| add dynamic thresholding to EGT | Excessive Gap Technique · Leduc-5 | nodes touched to converge: factor of 2 | Helped |
| add dynamic thresholding and RBP to CFR with Hedge | CFR with Hedge · Leduc-5 | nodes touched to converge: factor of 7 | Helped |
| add dynamic thresholding to regret matching | CFR with RM · Leduc | nodes touched to converge | No clear effect |
| vary Hedge threshold parameter d (ablation) | CFR with Hedge · Leduc | performance | No clear effect |
| use EGT threshold c of 0.05 instead of 0.001 to 0.01 (ablation) | EGT with dynamic thresholding · Leduc | performance | Hurt |
| use EGT threshold c of 0.001, 0.005 or 0.01 (ablation) | EGT · Leduc | performance | Helped |
| use Hedge with thresholding and RBP instead of RM with RBP | CFR · Leduc vs Leduc-5 | nodes touched to converge | Mixed |
Closest papers by meaning
- Solving Imperfect-Information Games via Discounted Regret Minimization (AAAI 2019 · similarity 0.92)
- Faster Game Solving via Hyperparameter Schedules (AAAI 2026 · similarity 0.91)
- Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions (NeurIPS 2019 · similarity 0.90)
- Learning in Games: Robustness of Fast Convergence (NeurIPS 2016 · similarity 0.90)
- Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games (NeurIPS 2024 · similarity 0.89)
- Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games (NeurIPS 2025 · similarity 0.88)
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.