What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects

• URL: http://arxiv.org/abs/2603.09532v1
• Date: Tue, 10 Mar 2026 11:40:42 GMT
• Title: What Do We Care About in Bandits with Noncompliance? BRACE: Bandits with Recommendations, Abstention, and Certified Effects
• Abstract summary: We show that recommendation welfare can strictly exceed every learner-measurable treatment policy when downstream actors use private information.<n>For finite-context square-IV problems we propose BRACE, a parameter-free phase-doubling algorithm that performs IV inversion only after matrix certification.<n>We complement the theory with a finite-context empirical benchmark spanning direct control, mediated present-versus-future tradeoffs, weak identification, homogeneity failure, and rectangular overidentification.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Bandits with noncompliance separate the learner's recommendation from the treatment actually delivered, so the learning target itself must be chosen. A platform may care about recommendation welfare in the current mediated workflow, treatment learning for a future direct-control regime, or anytime-valid uncertainty for one of those targets. These objectives need not agree. We formalize this objective-choice problem, identify the direct-control regime in which recommendation and treatment objectives collapse, and show by example that recommendation welfare can strictly exceed every learner-measurable treatment policy when downstream actors use private information. For finite-context square-IV problems we propose BRACE, a parameter-free phase-doubling algorithm that performs IV inversion only after matrix certification and otherwise returns full-range but honest structural intervals. BRACE delivers simultaneous policy-value validity, fixed-gap identification of the operationally optimal recommendation policy, and fixed-gap identification of the structurally optimal treatment policy under contextual homogeneity and invertibility. We complement the theory with a finite-context empirical benchmark spanning direct control, mediated present-versus-future tradeoffs, weak identification, homogeneity failure, and rectangular overidentification. The experiments show that safety appears as regret on easy problems, as abstention and wide valid intervals under weak identification, as a reason to prefer recommendation welfare under homogeneity failure, and as tighter structural uncertainty when extra instruments are available. For rich contexts, we also derive an orthogonal score whose conditional bias factorizes into compliance-model and outcome-model errors, clarifying what must be stabilized for anytime-valid semiparametric IV inference.

Related papers

• SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute [62.3458279176813]
  Self-Verifying Refinement is an oracle-free multi-turn reinforcement learning framework.<n>It learns to use self-verification as a compute-control policy.<n>It achieves a macro-average accuracy of 0.563 with only 2.99 inference turns on average.
  arXiv  Detail & Related papers  (2026-07-30T16:20:58Z)
• Efficient Online Conformal Selection with Limited Feedback [14.326282143930769]
  We address the problem of conformal selection, where an agent must select a minimal subset of options to ensure that at least one success'' is identified.<n>We show that the simple Adaptive Conformal Inference (ACI) update rule, when applied to the appropriate control parameter or dual variable, is both adversarially valid and efficient.
  arXiv  Detail & Related papers  (2026-05-14T15:22:46Z)
• RISED: A Pre-Deployment Safety Evaluation Framework for Clinical AI Decision-Support Systems [0.0]
  We propose a five-dimension pre-deployment evaluation covering Reliability, Inclusivity, Sensitivity, Equity, and Deployability.<n> RISED is released as an open-source Python package that supplies the quantitative verdicts existing clinical AI reporting standards require.
  arXiv  Detail & Related papers  (2026-05-13T02:17:13Z)
• Frictive Policy Optimization for LLMs: Epistemic Intervention, Risk-Sensitive Control, and Reflective Alignment [11.243856942345955]
  Frictive Policy Optimization (FPO) is a framework for learning language model policies that regulate what to say and when to intervene.<n>We introduce a compact taxonomy of frictive interventions, a structured friction functional that operationalizes multiple alignment failure modes, and a unified family of FPO methods spanning reward shaping, preference pairing, group-relative ranking, and risk-conditioned trust regions.
  arXiv  Detail & Related papers  (2026-04-28T02:24:51Z)
• Machine Learning for Stress Testing: Uncertainty Decomposition in Causal Panel Prediction [2.289837306672451]
  Regulatory stress testing requires projecting credit losses under hypothetical macroeconomic scenarios.<n>We propose a framework for policy-path counterfactual inference in panels.<n>We validate all results through simulation and semi-synthetic experiments with real unemployment data.
  arXiv  Detail & Related papers  (2026-03-08T03:22:38Z)
• Conditional Coverage Diagnostics for Conformal Prediction [47.93989136542648]
  We show that conditional coverage estimation can be a classification problem.<n>We call the resulting family of metrics excess risk of the target coverage (ERT)<n>We release an open-source package for ERT as well as previous conditional coverage metrics.
  arXiv  Detail & Related papers  (2025-12-12T18:47:39Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Optimal Baseline Corrections for Off-Policy Contextual Bandits [61.740094604552475]
  We aim to learn decision policies that optimize an unbiased offline estimate of an online reward metric. We propose a single framework built on their equivalence in learning scenarios. Our framework enables us to characterize the variance-optimal unbiased estimator and provide a closed-form solution for it.
  arXiv  Detail & Related papers  (2024-05-09T12:52:22Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Optimal Treatment Regimes for Proximal Causal Learning [7.672587258250301]
  We propose a novel optimal individualized treatment regime based on outcome and treatment confounding bridges. We show that the value function of this new optimal treatment regime is superior to that of existing ones in the literature.
  arXiv  Detail & Related papers  (2022-12-19T14:29:25Z)
• Post-Contextual-Bandit Inference [57.88785630755165]
  Contextual bandit algorithms are increasingly replacing non-adaptive A/B tests in e-commerce, healthcare, and policymaking. They can both improve outcomes for study participants and increase the chance of identifying good or even best policies. To support credible inference on novel interventions at the end of the study, we still want to construct valid confidence intervals on average treatment effects, subgroup effects, or value of new policies.
  arXiv  Detail & Related papers  (2021-06-01T12:01:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.