mlsanityData to 13 Oct 2026

Semiparametric Contextual Bandits

arXiv 1803.04204 ↗First posted 12 Mar 2018stat.ML cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term. We design new algorithms that achieve tildeO(d√T) regret over T rounds, when the linear function is d-dimensional, which matches the best known bounds for the simpler unconfounded case and improves on a recent result of Greenewald et al. (2017). Via an empirical evaluation, we show that our algorithms outperform prior approaches when there are non-linear confounding effects on the rewards. Technically, our algorithms use a new reward estimator inspired by doubly-robust approaches and our proofs require new concentration inequalities for self-normalized martingales.

Key facts. Cited by 19 papers in the map (data through 13 Oct 2026). First posted on arXiv 12 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 2; 2022: 5; 2023: 8; 2024: 0; 2025: 1; 2026: 2.

19 papers.

Sort:

By area:

  1. 2021Bias-Robust Bayesian Optimization via Dueling Banditscited by 11
  2. 2022A Robust Phased Elimination Algorithm for Corruption-Tolerant Gaussian Process Banditscited by 11
  3. 2019Contextual Multi-armed Bandit Algorithm for Semiparametric Reward Modelcited by 10
  4. 2021Model Selection for Generic Contextual Banditscited by 7
  5. 2023Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Riskcited by 7
  6. 2022Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventionscited by 6
  7. 2023RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventionscited by 5
  8. 2022Semi-Parametric Contextual Bandits with Graph-Laplacian Regularizationcited by 4
  9. 2023A Unified Framework of Policy Learning for Contextual Bandit with Confounding Bias and Missing Observationscited by 2
  10. 2022Flexible and Efficient Contextual Bandits with Heterogeneous Treatment Effect Oraclescited by 1
  11. 2023GBOSE: Generalized Bandit Orthogonalized Semiparametric Estimationcited by 1
  12. 2023Active and Passive Causal Inference Learningcited by 1
7 more
  1. 2025Experimental Design for Semiparametric Banditscited by 1
  2. 2022Statistical Estimation of Confounded Linear MDPs: An Instrumental Variable Approachcited by 0
  3. 2023Selective Uncertainty Propagation in Offline RLcited by 0
  4. 2023Ranking with Popularity Bias: User Welfare under Self-Amplification Dynamicscited by 0
  5. 2023Zero-Inflated Banditscited by 0
  6. 2026Nearly Optimal Best Arm Identification for Semiparametric Banditscited by 0
  7. 2026Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Banditscited by 0