mlsanityData to 14 Oct 2026

Online Policy Learning and Inference by Matrix Completion

arXiv 2404.17398 ↗First posted 26 Apr 2024stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 23 of its 55 references that are in the map. First posted on arXiv 26 Apr 2024.

Builds on

23 of 55 references.

References · 23

  1. 2019Implicit Regularization in Deep Matrix Factorizationcited by 405
  2. 2014Taming the Monster: A Fast and Simple Algorithm for Contextual Banditscited by 201
  3. 2014From Predictive to Prescriptive Analyticscited by 143
  4. 2014Matrix Completion and Low-Rank SVD via Fast Alternating Least Squarescited by 104
  5. 2019Confidence Intervals for Policy Evaluation in Adaptive Experimentscited by 95
  6. 2019Doubly robust off-policy evaluation with shrinkagecited by 87
  7. 2017Mostly Exploration-Free Algorithms for Contextual Banditscited by 85
  8. 2020High-Dimensional Sparse Linear Banditscited by 61
  9. 2019Noisy Matrix Completion: Understanding Statistical Guarantees for Convex Relaxation via Nonconvex Optimizationcited by 58
  10. 2019Bilinear Bandits with Low-rank Structurecited by 55
  11. 2016On Explore-Then-Commit Strategiescited by 47
  12. 2021Statistical Inference with M-Estimators on Adaptively Collected Datacited by 40
11 more
  1. 2021Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Banditscited by 40
  2. 2019Inference and Uncertainty Quantification for Noisy Matrix Completioncited by 39
  3. 2021Inference for Heteroskedastic PCA with Missing Datacited by 21
  4. 2019Statistical Inferences of Linear Forms for Noisy Matrix Completioncited by 18
  5. 2020Statistical Inference for Online Decision-Making: In a Contextual Bandit Settingcited by 17
  6. 2016Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descentcited by 15
  7. 2020Stochastic Low-rank Tensor Bandits for Multi-dimensional Online Decision Makingcited by 10
  8. 2022Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descentcited by 8
  9. 2021Inference for Low-Rank Modelscited by 7
  10. 2023High-dimensional Linear Bandits with Knapsackscited by 3
  11. 2023Multiple Testing of Linear Forms for Noisy Matrix Completioncited by 1

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Low-Rank Contextual Reinforcement Learning from Heterogeneous Human Feedbackcited by 10
  2. 2024Allocation Stability and Wald Inference under Variance-Aware UCBcited by 4
  3. 2024Matrix Completion via Residual Spectral Matchingcited by 0