Better algorithms for benign bandits
From MaRDI portal
Publication:4633809
Recommendations
Cited in
(20)- Weighted last-step min-max algorithm with improved sub-logarithmic regret
- Algorithms for adversarial bandit problems with multiple plays
- Non-stationary stochastic optimization
- scientific article; zbMATH DE number 6253908 (Why is no real title available?)
- A linear response bandit problem
- Sequential decision making with vector outcomes
- Bandits with switching costs, \(T^{2/3}\) regret
- Learning Theory
- Technical note: Nonstationary stochastic optimization under \(L_{p,q} \)-variation measures
- Regret bounded by gradual variation for online convex optimization
- Online convex optimization in the bandit setting: gradient descent without a gradient
- Bandit regret scaling with the effective loss range
- Sparsity, variance and curvature in multi-armed bandits
- Extracting certainty from uncertainty: regret bounded by variation in costs
- Ballooning multi-armed bandits
- Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits
- Bandits with global convex constraints and objective
- Volumetric spanners: an efficient exploration basis for learning
- Profile-based bandit with unknown profiles
- Improving multi-armed bandit algorithms in online pricing settings
This page was built for publication: Better algorithms for benign bandits
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4633809)