2 papers
cs.LG2023
Nash Regret Guarantees for Linear Bandits
Ayush Sawarni, Soumybrata Pal, Siddharth Barman
We obtain essentially tight upper bounds for a strengthened notion of regret in the stochastic linear bandits framework. The strengthening -- referred to as Nash regret -- is defin…
cs.LG2023
Learning Good Interventions in Causal Graphs via Covering
Ayush Sawarni, Rahul Madhavan, Gaurav Sinha +1
We study the causal bandit problem that entails identifying a near-optimal intervention from a specified set of (possibly non-atomic) interventions over a given causal graph. H…