Research map / Probabilistic and scientific modeling / Treatment effects
Bounding Causal Effects on Continuous Outcome
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add causal bounds estimated from 9650 observational samples to kl-UCB | kl-UCB · International Stroke Trial | cumulative regret: 38.63 -> 0.07 | Helped |
| Use causal bounds estimated from only 300 samples (ablation) | kl-UCBc · International Stroke Trial | cumulative regret: 38.63 -> 37.94 | No clear effect |
| Warm-start kl-UCB with empirical estimates of E[Y∣x,z] (ablation) | kl-UCB · International Stroke Trial | cumulative regret: 38.63 -> 373.42 | Hurt |
| Add empirical causal bounds estimated from 9711 observations to lil’LUCB | lil’LUCB · International Stroke Trial | stopping time: 6.5 × 10³ -> 4.4 × 10³ | Helped |
| Use empirical causal bounds from only 100 observations (ablation) | lil’LUCBc · International Stroke Trial | stopping time: 6.5 × 10³ -> 6.5 × 10³ | No clear effect |
| Warm-start lil’LUCB with estimates of E[Y∣x] (ablation) | lil’LUCB · International Stroke Trial | stopping time: 6.5 × 10³ -> 8.2 × 10³ | Hurt |
| Add causal bounds estimated from 9650 observational samples to D-UCB | D-UCB · International Stroke Trial | cumulative regret: 111.8 -> 0.07 | Helped |
| Use causal bounds from only 300 samples (ablation) | D-UCBc · International Stroke Trial | cumulative regret: 111.8 -> 110.8 | No clear effect |
| Seed D-UCB with samples of confounded observations (ablation) | D-UCB · International Stroke Trial | cumulative regret: 111.8 -> 153.9 | Hurt |
| Clip UCB confidence bounds using valid causal effect bounds | UCB-style bandit algorithms · IV and contextual IV bandits | asymptotic regret bound: The causal bounds restrict the regret sum to suboptimal arms or policies whose upper causal bound reaches the optimal re | Helped |
Closest papers by meaning
- Beyond the Average: Distributional Causal Inference under Imperfect Compliance (NeurIPS 2025 · similarity 0.89)
- Impossibility of Distribution-Free Predictive Inference for Individual Treatment Effects (NeurIPS 2026 · similarity 0.88)
- Conformal Prediction for Causal Effects of Continuous Treatments (NeurIPS 2025 · similarity 0.86)
- Continuous Treatment Effects with Surrogate Outcomes (ICML 2024 · similarity 0.86)
- Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding (NeurIPS 2024 · similarity 0.86)
- Causal Attribution Analysis for Continuous Outcomes (ICML 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.