DeepAI AI Chat
Log In Sign Up

Nonparametric Learning and Optimization with Covariates

by   Ningyuan Chen, et al.

Modern decision analytics frequently involves the optimization of an objective over a finite horizon where the functional form of the objective is unknown. The decision analyst observes covariates and tries to learn and optimize the objective by experimenting with the decision variables. We present a nonparametric learning and optimization policy with covariates. The policy is based on adaptively splitting the covariate space into smaller bins (hyper-rectangles) and learning the optimal decision in each bin. We show that the algorithm achieves a regret of order O((T)^2 T^(2+d)/(4+d)), where T is the length of the horizon and d is the dimension of the covariates, and show that no policy can achieve a regret less than O(T^(2+d)/(4+d)) and thus demonstrate the near optimality of the proposed policy. The role of d in the regret is not seen in parametric learning problems: It highlights the complex interaction between the nonparametric formulation and the covariate dimension. It also suggests the decision analyst should incorporate contextual information selectively.


page 1

page 2

page 3

page 4


Dimension Reduction in Contextual Online Learning via Nonparametric Variable Selection

We consider a contextual online learning (multi-armed bandit) problem wi...

Generalized Policy Elimination: an efficient algorithm for Nonparametric Contextual Bandits

We propose the Generalized Policy Elimination (GPE) algorithm, an oracle...

Semi-parametric dynamic contextual pricing

We consider a canonical revenue maximization problem where customers arr...

Functional Sequential Treatment Allocation with Covariates

We consider a multi-armed bandit problem with covariates. Given a realiz...

Nonparametric Matrix Estimation with One-Sided Covariates

Consider the task of matrix estimation in which a dataset X ∈ℝ^n× m is o...

Dynamic Assortment Optimization with Changing Contextual Information

In this paper, we study the dynamic assortment optimization problem unde...