GraphDR-LinUCB projects contextual bandit arms onto a graph's low-frequency eigenspace to obtain the first Õ(k√T) regret bound under approximate smoothness, with a spectral predictor Γ_k that matches outcomes on five of six real datasets.
From Bandits to Experts: On the Value of Side-Observations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
We consider an adversarial online learning setting where a decision maker can choose an action in every stage of the game. In addition to observing the reward of the chosen action, the decision maker gets side observations on the reward he would have obtained had he chosen some of the other actions. The observation structure is encoded as a graph, where node i is linked to node j if sampling i provides information on the reward of j. This setting naturally interpolates between the well-known "experts" setting, where the decision maker can view all rewards, and the multi-armed bandits setting, where the decision maker can only view the reward of the chosen action. We develop practical algorithms with provable regret guarantees, which depend on non-trivial graph-theoretic properties of the information feedback structure. We also provide partially-matching lower bounds.
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph Dimensionality Reduction for Contextual Bandits: Structure-Specific Regret Bounds under Approximate Smoothness and Noisy Eigenspaces
GraphDR-LinUCB projects contextual bandit arms onto a graph's low-frequency eigenspace to obtain the first Õ(k√T) regret bound under approximate smoothness, with a spectral predictor Γ_k that matches outcomes on five of six real datasets.