arXiv research

The paper addresses statistical estimation in MDPs with confounders using instrumental variables.

Paper develops IV method for consistent OPE in confounded MDPs.

New bounds assess policy evaluation under unobserved confounders, showing model-based methods are more effective.

Paper develops a method to estimate value of a policy in confounded MDPs.

New methods for evaluating and optimizing policies in offline RL with unobserved confounders.

New algorithm tackles confounding in offline RL for partially observable MDPs.

New algorithm learns optimal policies in strategic MDPs with private types.

PRL improves off-policy evaluation in partially observed MDPs.

We develop efficient and sharp bounds on policy value under perturbations in MDPs.

The paper proposes a method to precisely decompose confounders and estimate treatment effects.

Research shows continual learning challenges in confounded datasets.

Statistical learning on biological data can be challenging due to confounding variables in sample collection and processing. Confounders can cause models to generalize poorly and result in inaccurate prediction performance metrics if models are not validated thoroughly. In this paper, we propose methods to control for …

Adaptive reduction scheme approximates optimal policy in regularized MDPs.

Causal inference from observational data requires assumptions. These assumptions range from measuring confounders to identifying instruments. Traditionally, causal inference assumptions have focused on estimation of effects for a single treatment. In this work, we construct techniques for estimation with multiple treat…

We study Exo-MDPs to reduce sample complexity in reinforcement learning.

Detect hidden confounding in observational data using multiple environments.

Machine learning confound removal biases results, leading to misleading predictions.

KRCD detects unobserved confounders in nonlinear observational data.

In this paper, a sparse Markov decision process (MDP) with novel causal sparse Tsallis entropy regularization is proposed.The proposed policy regularization induces a sparse and multi-modal optimal policy distribution of a sparse MDP. The full mathematical analysis of the proposed sparse MDP is provided.We first analyz…

Study identifies conditions for proxy adjustment in confounded binary treatment outcomes.

New method estimates policy performance under unobserved confounding.

Consistent estimator derived for confounding strength in observational data.

A new method uses randomized trials to estimate the strength of unobserved confounding.

Paper establishes new lower bounds for MDPs with changing transition kernels.

This paper tackles confounding biases in data augmentation.

We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) algorithms especially when the number of items is huge. In this paper, we present …

New method recovers latent confounders from high-dimensional proxy variables.

Proposes tests to control confounding bias in predictive models.

New method tackles confounded bandit problems with dual instrumental variables.

New approach for causal inference with interdependent, time-varying latent confounders.

Causal discovery from data affected by latent confounders is an important and difficult challenge. Causal functional model-based approaches have not been used to present variables whose relationships are affected by latent confounders, while some constraint-based methods can present them. This paper proposes a causal f…

Estimating the individual treatment effect (ITE) from observational data is essential in medicine. A central challenge in estimating the ITE is handling confounders, which are factors that affect both an intervention and its outcome. Most previous work relies on the unconfoundedness assumption, which posits that all th…

New method approximates POMDPs with PB-MDPs, providing error bounds and practical algorithms.

CARE improves LLM aggregation by accounting for shared confounders.

Proposes BDCM to handle unmeasured confounders in causal inference.

New methods prioritize acquiring confounding features for efficient treatment effect estimation.

Valid causal inference with unobserved confounding in high-dimensional settings.

Spectral deconfounding improves machine learning models by reducing hidden confounding effects.

We propose a method for inferring the existence of a latent common cause ('confounder') of two observed random variables. The method assumes that the two effects of the confounder are (possibly nonlinear) functions of the confounder plus independent, additive noise. We discuss under which conditions the model is identi…

Study shows how adjusting for a binary proxy can bound causal effects.

We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimen…

Paper tackles unobserved confounding in human-AI collaborations.

SpaCE tackles spatial confounding in scientific studies.

Estimates causal effects with selection bias and confounding using regression.

Paper tackles backwards-compatible data adaptation for confounded covariate and label shifts.

Deep CITs test conditional independence in images, improving brain MRI scan analysis.

Optimizes learning policies in MDPs with weakly communicating structure.

In this paper, we study the confounder detection problem in the linear model, where the target variable $Y$ is predicted using its $n$ potential causes $X_n=(x_1,...,x_n)^T$. Based on an assumption of rotation invariant generating process of the model, recent study shows that the spectral measure induced by the regress…