Better algorithms for benign bandits
From MaRDI portal
Publication:4633809
zbMATH Open1425.91084MaRDI QIDQ4633809FDOQ4633809
Authors: Elad Hazan, Satyen Kale 
Publication date: 6 May 2019
Full work available at URL: https://dl.acm.org/citation.cfm?id=1496775
Recommendations
Learning and adaptive systems in artificial intelligence (68T05) Decision theory (91B06) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)
Cited In (20)
- Title not available (Why is that?)
- Extracting certainty from uncertainty: regret bounded by variation in costs
- Profile-based bandit with unknown profiles
- Sequential decision making with vector outcomes
- Algorithms for adversarial bandit problems with multiple plays
- Ballooning multi-armed bandits
- Improving multi-armed bandit algorithms in online pricing settings
- Regret bounded by gradual variation for online convex optimization
- Greedy Algorithm Almost Dominates in Smoothed Contextual Bandits
- Volumetric spanners: an efficient exploration basis for learning
- Weighted last-step min-max algorithm with improved sub-logarithmic regret
- A linear response bandit problem
- Non-stationary stochastic optimization
- Bandit regret scaling with the effective loss range
- Sparsity, variance and curvature in multi-armed bandits
- Online convex optimization in the bandit setting: gradient descent without a gradient
- Bandits with global convex constraints and objective
- Technical note: Nonstationary stochastic optimization under \(L_{p,q} \)-variation measures
- Learning Theory
- Bandits with switching costs, \(T^{2/3}\) regret
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)
