Research map / Bandits and online learning / Online convex optimization and games
On the Complexity of Adversarial Decision Making
Dylan J Foster, Alexander Rakhlin, Ayush Sekhari, Karthik Sridharan
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 convexified DEC to characterize model-class complexity | Adversarial decision making · Adversarial DMSO | regret: \RegDM \leq{} \comp[1/8\eta](\mathrm{co}(\cM))\cdot{}T + \frac{2}{\eta} \cdot\log(\abs{\Pi}/\delta) | Improved |
| Convexify the model class when measuring DEC | Adversarial decision making · Adversarial DMSO | minimax regret: \comp(\mathrm{co}(\cM)) | Mixed |
| Use high-probability Exploration-by-Optimization with an exponential-moment objective | ExO+ · Adaptive adversaries in DMSO | high-probability regret: \RegDM \leq{} \comp[1/8\eta](\mathrm{co}(\cM))\cdot{}T + \frac{2}{\eta} \cdot\log(\abs{\Pi}/\delta) | Improved |
Closest papers by meaning
- An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs (ICLR 2026 · similarity 0.90)
- Sparsity-Agnostic Linear Bandits with Adaptive Adversaries (NeurIPS 2024 · similarity 0.90)
- Information Capacity Regret Bounds for Bandits with Mediator Feedback (JMLR 2024 · similarity 0.89)
- Regret Minimization via Saddle Point Optimization (NeurIPS 2023 · similarity 0.89)
- Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback (NeurIPS 2025 · similarity 0.89)
- Near-Optimal Regret in Adversarial Kernel Bandits (NeurIPS 2026 · 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.
