Research map / Bandits and online learning / Online convex optimization and games
Conic Blackwell Algorithm: Parameter-Free Convex-Concave Saddle-Point Solving
Julien Grand-Clément, Christian Kroer
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 CBA+ instead of OMD/FTRL variants at theoretical step size (alpha=1) | CBA+ · DRO logistic classification (synthetic, splice, madelon) | worst-case loss vs steps | Improved |
| multiply baseline step size by alpha=1,000 | OMD/FTRL baselines · DRO synthetic data | worst-case loss vs steps | Mixed |
| multiply baseline step size by alpha=10,000 | OMD/FTRL baselines · DRO synthetic and splice | worst-case loss vs steps | Hurt |
| use CBA+ instead of RM+ on matrix games and EFGs | CBA+ · matrix games, Leduc, Battleship | duality gap vs steps | No clear effect |
| use CBA+ instead of AdaHedge and AdaFTRL | CBA+ · synthetic matrix games | duality gap vs steps | Improved |
| use CBA+ instead of OMD, FTRL variants on DRO wall-clock | CBA+ · DRO instance | running time: 2x-2.5x faster; 3x-4x faster | Improved |
Closest papers by meaning
- Extensive-Form Game Solving via Blackwell Approachability on Treeplexes (NeurIPS 2024 · similarity 0.89)
- Faster Game Solving via Predictive Blackwell Approachability: Connecting Regret Matching and Mirror Descent (AAAI 2021 · similarity 0.88)
- Solving a Class of Non-Convex Min-Max Games Using Iterative First Order Methods (NeurIPS 2019 · similarity 0.87)
- Thresholds for sensitive optimality and Blackwell optimality in stochastic games (NeurIPS 2025 · similarity 0.87)
- Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points (NeurIPS 2026 · similarity 0.87)
- From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization (NeurIPS 2024 · similarity 0.85)
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.
