154 citations · 474 across the 50 of their papers we have counts for
4 papers · 2 filters
Robust Causal Bandits for Linear Models
Zirui Yan, Arpan Mukherjee, Burak Varıcı +1
Sequential design of experiments for optimizing a reward function in causal systems can be effectively modeled by the sequential design of interventions in causal bandits (CBs). In…
Optimal Best Arm Identification with Fixed Confidence in Restless Bandits
P. N. Karthik, Vincent Y. F. Tan, Arpan Mukherjee +1
We study best arm identification in a restless multi-armed bandit setting with finitely many arms. The discrete-time data generated by each arm forms a homogeneous Markov chain tak…
Score-based Causal Representation Learning with Interventions
Burak Varici, Emre Acarturk, Karthikeyan Shanmugam +2
This paper studies the causal representation learning problem when the latent causal variables are observed indirectly through an unknown linear transformation. The objectives are:…
Best Arm Identification in Stochastic Bandits: Beyond optimality
Arpan Mukherjee, Ali Tajer
This paper investigates a hitherto unaddressed aspect of best arm identification (BAI) in stochastic multi-armed bandits in the fixed-confidence setting. Two key metrics for assess…