Kernel Single Proxy Control for Deterministic Confounding

• URL: http://arxiv.org/abs/2308.04585v3
• Date: Tue, 20 Feb 2024 13:08:31 GMT
• Title: Kernel Single Proxy Control for Deterministic Confounding
• Authors: Liyuan Xu, Arthur Gretton
• Abstract summary: We show that a single proxy variable is sufficient for causal estimation if the outcome is generated deterministically. We prove and empirically demonstrate that we can successfully recover the causal effect on challenging synthetic benchmarks.
• Score: 32.70182383946395
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of causal effect estimation with an unobserved confounder, where we observe a proxy variable that is associated with the confounder. Although Proxy causal learning (PCL) uses two proxy variables to recover the true causal effect, we show that a single proxy variable is sufficient for causal estimation if the outcome is generated deterministically, generalizing Control Outcome Calibration Approach (COCA). We propose two kernel-based methods for this setting: the first based on the two-stage regression approach, and the second based on a maximum moment restriction approach. We prove that both approaches can consistently estimate the causal effect, and we empirically demonstrate that we can successfully recover the causal effect on challenging synthetic benchmarks.

Related papers

• Counterfactual Realizability [52.85109506684737]
  We introduce a formal definition of realizability, the ability to draw samples from a distribution, and then develop a complete algorithm to determine whether an arbitrary counterfactual distribution is realizable. We illustrate the implications of this new framework for counterfactual data collection using motivating examples from causal fairness and causal reinforcement learning.
  arXiv  Detail & Related papers  (2025-03-14T20:54:27Z)
• Density Ratio-based Proxy Causal Learning Without Density Ratios [26.49087216375106]
  We address the setting of Proxy Causal Learning (PCL), which has the goal of estimating causal effects from observed data in the presence of hidden confounding. Two approaches have been proposed to perform causal effect estimation given proxy variables. We propose a practical and effective implementation of the second approach, which bypasses explicit density ratio estimation and is suitable for continuous and high-dimensional treatments.
  arXiv  Detail & Related papers  (2025-03-11T12:27:54Z)
• Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework [77.45983464131977]
  We focus on how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications. Our research identifies two critical latent factors affecting RAG's confidence in its predictions. We develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers.
  arXiv  Detail & Related papers  (2024-09-24T14:52:14Z)
• Automating the Selection of Proxy Variables of Unmeasured Confounders [16.773841751009748]
  We extend the existing proxy variable estimator to accommodate scenarios where multiple unmeasured confounders exist between the treatments and the outcome. We propose two data-driven methods for the selection of proxy variables and for the unbiased estimation of causal effects.
  arXiv  Detail & Related papers  (2024-05-25T08:53:49Z)
• Valid Inference After Causal Discovery [73.87055989355737]
  We develop tools for valid post-causal-discovery inference. We show that a naive combination of causal discovery and subsequent inference algorithms leads to highly inflated miscoverage rates.
  arXiv  Detail & Related papers  (2022-08-11T17:40:45Z)
• On Testability of the Front-Door Model via Verma Constraints [7.52579126252489]
  Front-door criterion can be used to identify and compute causal effects despite unmeasured confounders. Key assumptions -- the existence of a variable that fully mediates the effect of the treatment on the outcome, and which simultaneously does not suffer from similar issues of confounding -- are often deemed implausible. We show that under mild conditions involving an auxiliary variable, the assumptions encoded in the front-door model may be tested via generalized equality constraints.
  arXiv  Detail & Related papers  (2022-03-01T00:38:29Z)
• Partial Identification with Noisy Covariates: A Robust Optimization Approach [94.10051154390237]
  Causal inference from observational datasets often relies on measuring and adjusting for covariates. We show that this robust optimization approach can extend a wide range of causal adjustment methods to perform partial identification. Across synthetic and real datasets, we find that this approach provides ATE bounds with a higher coverage probability than existing methods.
  arXiv  Detail & Related papers  (2022-02-22T04:24:26Z)
• False Correlation Reduction for Offline Reinforcement Learning [115.11954432080749]
  We propose falSe COrrelation REduction (SCORE) for offline RL, a practically effective and theoretically provable algorithm. We empirically show that SCORE achieves the SoTA performance with 3.1x acceleration on various tasks in a standard benchmark (D4RL)
  arXiv  Detail & Related papers  (2021-10-24T15:34:03Z)
• Estimation of Bivariate Structural Causal Models by Variational Gaussian Process Regression Under Likelihoods Parametrised by Normalising Flows [74.85071867225533]
  Causal mechanisms can be described by structural causal models. One major drawback of state-of-the-art artificial intelligence is its lack of explainability.
  arXiv  Detail & Related papers  (2021-09-06T14:52:58Z)
• Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation [26.47311758786421]
  Proxy causal learning (PCL) is a method for estimating the causal effect of treatments on outcomes in the presence of unobserved confounding. We propose a novel method for PCL, the deep feature proxy variable method (DFPV), to address the case where the proxies, treatments, and outcomes are high-dimensional and have nonlinear complex relationships.
  arXiv  Detail & Related papers  (2021-06-07T18:36:13Z)
• Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restriction [39.51144507601913]
  We focus on the proximal causal learning setting, but our methods can be used to solve a wider class of inverse problems characterised by a Fredholm integral equation. We provide consistency guarantees for each algorithm, and we demonstrate these approaches achieve competitive results on synthetic data and data simulating a real-world task.
  arXiv  Detail & Related papers  (2021-05-10T17:52:48Z)
• Causal Mediation Analysis with Hidden Confounders [24.246450472404614]
  Causal mediation analysis (CMA) is a formal statistical approach for identifying and estimating causal effects. This work aims to circumvent the stringent assumption by following a causal graph with a unified confounder and its proxy variables. Our core contribution is an algorithm that combines deep latent-variable models and proxy strategy to jointly infer a unified surrogate confounder and estimate different causal effects in CMA from observed variables.
  arXiv  Detail & Related papers  (2021-02-21T06:46:11Z)
• Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders [62.54431888432302]
  We study an OPE problem in an infinite-horizon, ergodic Markov decision process with unobserved confounders. We show how, given only a latent variable model for states and actions, policy value can be identified from off-policy data.
  arXiv  Detail & Related papers  (2020-07-27T22:19:01Z)
• Almost-Matching-Exactly for Treatment Effect Estimation under Network Interference [73.23326654892963]
  We propose a matching method that recovers direct treatment effects from randomized experiments where units are connected in an observed network. Our method matches units almost exactly on counts of unique subgraphs within their neighborhood graphs.
  arXiv  Detail & Related papers  (2020-03-02T15:21:20Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

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.