The paper introduces a semiparametric framework for counterfactual regression along a specified incremental‑intervention path. It estimates a finite‑dimensional constrained projection of counterfactual risk using cross‑fitted influence‑function representations, and establishes consistency, local stability, and first‑order expansions for smooth and finite‑dimensional programs. The results provide asymptotically valid inference, including simultaneous confidence bands, and are demonstrated through simulations and an SMS reminder application.
arXiv:2607. 05620v1 Announce Type: cross Abstract: In many decision-making settings, new interventions are acceptable only if they do not reduce outcomes below some established threshold.
arXiv:2606. 07399v1 Announce Type: cross Abstract: Generative models for counterfactual outcomes have great potential to support decision-making under complex interventions, but existing approaches are limited by unstable estimation, poor generalization across environments, and bias from nuisance model misspecification.
arXiv:2609.07917v1 Announce Type: cross Abstract: Counterfactual explanations formalize "what-if" scenarios by identifying modifications to an input instance that obtain a desired alternative predict...
arXiv:2608. 02893v1 Announce Type: cross Abstract: Counterfactual inference approaches for sequential decision-making typically assume deterministic causal models, where all randomness stems from latent variables.
arXiv:2607. 21806v1 Announce Type: new Abstract: Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice.
FCx is a new algorithm that generates counterfactual explanations while explicitly enforcing feasibility constraints. It uses a modified Variational Autoencoder with a multi‑factor loss to produce realistic, low‑cost counterfactuals that satisfy both hard constraints supplied by users and soft constraints inferred via causal inference. Experiments on four public datasets demonstrate that FCx matches state‑of‑the‑art performance across multiple metrics while guaranteeing feasibility.
arXiv:2608. 13209v1 Announce Type: cross Abstract: Many operational decisions are sequences of interventions under a cumulative resource limit, such as a maintenance schedule within a crew-hour budget.
arXiv:2501.06926v5 Announce Type: replace Abstract: Double reinforcement learning (DRL) provides efficient off-policy inference for policy values in nonparametric Markov decision processes (MDPs), bu...
The paper introduces SC2R, a semantics‑constrained counterfactual recourse framework designed to provide actionable, feasible intervention plans for students identified as at risk by learning analytics models. SC2R integrates a calibrated predictive model, integer‑programming recourse generation over discrete actions, an RDF vocabulary for representing intervention plans, and SHACL validation to enforce constraints such as timing, budget, immutability, and availability. Evaluated on the OULAD dataset, the framework demonstrates strong predictive performance, scalable generation of compact intervention plans, and the ability to detect infeasible plans that would otherwise be accepted by simpler optimization approaches.
arXiv:2607. 27263v1 Announce Type: new Abstract: Most benchmarks for causal inference over time series are observational, small, or domain-specific, leaving interventional and counterfactual estimation under-served exactly where it matters most, such as in healthcare, policy evaluation, and climate science.
The paper introduces a method for learning risk scores that remain reliable even when historical data contain unobserved confounders. By treating propensity weights as uncertain and applying sensitivity analysis with Wasserstein distributionally robust optimization, the authors formulate a robust learning problem solvable via an exponential cone program. Experiments on semi‑synthetic UCI data show the approach improves calibration by up to 29.2% over traditional benchmarks and 11.1% over the state of the art, without harming other performance metrics.
arXiv:2608. 08743v1 Announce Type: cross Abstract: Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time.