Online Policy Learning and Inference by Matrix Completion
Is it possible to make online decisions when personalized covariates are unavailable? We take a collaborative-filtering approach for decision-making based on collective preferences. By assuming low-dimensional latent features, we formulate the covariate-free decision-making problem as a matrix completion bandit. We propose a policy learning procedure that combines an $\varepsilon$-greedy policy for decision-making with an online gradient descent algorithm for bandit parameter estimation. Our novel two-phase design balances policy learning accuracy and regret performance. For policy inference, we develop an online debiasing method based on inverse propensity weighting and establish its asymptotic normality. Our methods are applied to data from the San Francisco parking pricing project, revealing intriguing discoveries and outperforming the benchmark policy.
Code (0)
등록된 구현이 없습니다.
Tasks
Collaborative FilteringDecision MakingMatrix Completionparameter estimationSimilar Papers 제목 키워드 기반
Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning
Generative models such as diffusion and flow-matching offer expressive policies for offline reinforcement learning (RL) by capturing rich, multimodal action distributions, but their iterative sampling introduces high inf…
Action GenerationDecision MakingOffline RLReinforcement Learning (RL)+1Always Valid Risk Monitoring for Online Matrix Completion
Always-valid concentration inequalities are increasingly used as performance measures for online statistical learning, notably in the learning of generative models and supervised learning. Such inequality advances the on…
Matrix CompletionvalidMatrix Completion Under Monotonic Single Index Models
Most recent results in matrix completion assume that the matrix under consideration is low-rank or that the columns are in a union of low-rank subspaces. In real-world settings, however, the linear structure underlying t…
Matrix CompletionDeep Learning Approach for Matrix Completion Using Manifold Learning
Matrix completion has received vast amount of attention and research due to its wide applications in various study fields. Existing methods of matrix completion consider only nonlinear (or linear) relations among entries…
Deep LearningMatrix CompletionMulti-Task LearningSolving the Robust Matrix Completion Problem via a System of Nonlinear Equations
We consider the problem of robust matrix completion, which aims to recover a low rank matrix $L_*$ and a sparse matrix $S_*$ from incomplete observations of their sum $M=L_*+S_*\in\mathbb{R}^{m\times n}$. Algorithmically…
Matrix Completion