Research map / Bandits and online learning / Online convex optimization and games
Regret Minimization via Saddle Point Optimization
Johannes Kirschner, Alireza Bakhtiari, Kushagra Chandak, Volodymyr Tkachuk, Csaba Szepesvari
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 Anytime-E2D instead of E2D with lambda tuned for horizon n=200 | Anytime-E2D · Semi-bandit with revealing action, d=3, n=2000 | regret | Improved |
| use Anytime-E2D instead of E2D with lambda tuned for horizon n=500 | Anytime-E2D · Semi-bandit with revealing action, d=3, n=2000 | regret | Improved |
| use Anytime-E2D instead of E2D with lambda tuned for horizon n=1000 | Anytime-E2D · Semi-bandit with revealing action, d=3, n=2000 | regret | Improved |
| tune E2D lambda for the correct horizon n=2000 | E2D · Semi-bandit with revealing action, d=3, n=2000 | regret | No clear effect |
| replace gaps Delta with Delta_f in both algorithms | E2D and Anytime-E2D · semi-bandit experiments | regret | Improved |
| use Anytime-E2D with adaptive scale instead of lambda set for d*sqrt(n) bound | Anytime-E2D · Semi-bandit, d=30, n=1000 | regret | Improved |
Closest papers by meaning
- Model-Free Reinforcement Learning with the Decision-Estimation Coefficient (NeurIPS 2023 · similarity 0.90)
- p-Mean Regret for Stochastic Bandits (AAAI 2025 · similarity 0.88)
- Bayesian Regret Minimization in Offline Bandits (ICML 2024 · similarity 0.88)
- Regret minimization in Linear Bandits with offline data via extended D-optimal exploration. (NeurIPS 2026 · similarity 0.87)
- Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling (ICML 2024 · similarity 0.87)
- Best of Both Worlds: Regret Minimization versus Minimax Play (ICML 2025 · similarity 0.87)
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.
