
Model Selection for Generic Contextual Bandits
We consider the problem of model selection for the general stochastic co...
read it

Parameter and Feature Selection in Stochastic Linear Bandits
We study two model selection settings in stochastic linear bandits (LB)....
read it

No Regrets for Learning the Prior in Bandits
We propose AdaTS, a Thompson sampling algorithm that adapts sequentially...
read it

Collaborative Learning and Personalization in MultiAgent Stochastic Linear Bandits
We consider the problem of minimizing regret in an N agent heterogeneous...
read it

Pareto Optimal Model Selection in Linear Bandits
We study a model selection problem in the linear bandit setting, where t...
read it

Minimax Optimal Algorithms for Adversarial Bandit Problem with Multiple Plays
We investigate the adversarial bandit problem with multiple plays under ...
read it

Thresholded LASSO Bandit
In this paper, we revisit sparse stochastic contextual linear bandits. I...
read it
ProblemComplexity Adaptive Model Selection for Stochastic Linear Bandits
We consider the problem of model selection for two popular stochastic linear bandit settings, and propose algorithms that adapts to the unknown problem complexity. In the first setting, we consider the K armed mixture bandits, where the mean reward of arm i ∈ [K], is μ_i+ 〈α_i,t,θ^* 〉, with α_i,t∈R^d being the known context vector and μ_i ∈ [1,1] and θ^* are unknown parameters. We define θ^* as the problem complexity and consider a sequence of nested hypothesis classes, each positing a different upper bound on θ^*. Exploiting this, we propose Adaptive Linear Bandit (ALB), a novel phase based algorithm that adapts to the true problem complexity, θ^*. We show that ALB achieves regret scaling of O(θ^*√(T)), where θ^* is apriori unknown. As a corollary, when θ^*=0, ALB recovers the minimax regret for the simple bandit algorithm without such knowledge of θ^*. ALB is the first algorithm that uses parameter norm as model section criteria for linear bandits. Prior state of art algorithms <cit.> achieve a regret of O(L√(T)), where L is the upper bound on θ^*, fed as an input to the problem. In the second setting, we consider the standard linear bandit problem (with possibly an infinite number of arms) where the sparsity of θ^*, denoted by d^* ≤ d, is unknown to the algorithm. Defining d^* as the problem complexity, we show that ALB achieves O(d^*√(T)) regret, matching that of an oracle who knew the true sparsity level. This is the first algorithm that achieves such model selection guarantees resolving an open problem in <cit.>. We further verify through synthetic and realdata experiments that the performance gains are fundamental and not artifacts of mathematical bounds.
READ FULL TEXT
Comments
There are no comments yet.