Generative AI for Validating Physics Laws
arXiv:2503.17894v3 Announce Type: replace-cross Abstract: We propose generative learner for estimating heterogeneous treatment effects and characterizing the full distribution of causal effects. The...
arXiv:2503.17894v3 Announce Type: replace-cross Abstract: We propose generative learner for estimating heterogeneous treatment effects and characterizing the full distribution of causal effects. The...
arXiv:2607. 04360v1 Announce Type: cross Abstract: Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and applied domains.
ACTIVA is a transformer‑based conditional variational autoencoder designed to estimate full interventional distributions from observational data without requiring interventional data, a causal graph, or per‑task fitting. It learns a conditional latent prior that amortizes causal knowledge across diverse training tasks, enabling a single forward pass to handle new causal models drawn from the training distribution. Empirical results on synthetic and biologically realistic gene‑expression simulations show that ACTIVA outperforms correlational baselines, reduces spurious non‑descendant effects, and matches strong amortized baselines, while also validating its theoretical mixture‑of‑distributions property on observationally equivalent models.
arXiv:2608. 08204v1 Announce Type: cross Abstract: This work proposes deep nonparametric Instrumental variable quantile regression (IVQR), a two-stage estimator that combines conditional diffusion modeling with a kernel-smoothed conditional moment formulation.
Conditional generative models have emerged as powerful tools for sampling from target conditional distributions, driving substantial advances across a wide range of scientific and applied domains. As these models proliferate, practitioners often face multiple plausible generators whose performance can vary with the task, data, or input condition.
arXiv:2606. 21806v2 Announce Type: replace Abstract: Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains.
The paper introduces CauVaDE, a causal generative model that represents an unobserved confounder as a discrete latent cluster, enabling accurate approximation of both observational and interventional image distributions. It demonstrates that this representation can capture diverse causal explanations without sacrificing fit to the data. A novel causal bootstrap method is proposed to vary confounder entropy, producing a family of distinct interventional image distributions.
arXiv:2605. 01765v2 Announce Type: replace-cross Abstract: Mediation analysis has traditionally focused on outcome-level summary contrasts, such as mean effects, which may obscure substantial distributional changes induced by complex and nonlinear causal mechanisms.
OrthoGen introduces a generative orthogonal learner for estimating conditional distributional potential outcomes (CDPOs) under time‑varying treatments, addressing challenges of time‑varying confounding. It combines a generative recursive g‑computation adjustment strategy with Neyman‑orthogonal, doubly robust learning, achieving rate double robustness and quasi‑oracle efficiency. The method is flexible, supporting various generative backbones, and demonstrates strong performance on synthetic, semi‑synthetic, and real‑world datasets.
Residual-Based Causal Discovery via Pretrained In-Context Quantile Regression proposes Loscar, an extension of the RESIT framework to location-scale noise models (LSNMs). Loscar estimates conditional mean and scale using quantile regression, allowing pretrained tabular foundation models to serve as plug‑in estimators. Experiments on bivariate and multivariate causal‑discovery benchmarks show that in‑context quantile regression outperforms a feasible generalized least squares (FGLS) variant, especially when causes are multivariate.
arXiv:2603. 12037v2 Announce Type: replace Abstract: Foundation models based on prior-data fitted networks (PFNs) have shown strong empirical performance in causal inference by framing the task as an in-context learning problem.
The paper introduces the transport Neural Tangent Kernel (tNTK) to enable active learning for conditional generative models that produce distributional outputs. By decomposing the Wasserstein test risk into mean and shape components, the authors show that mean‑based active learning misses distributional shape, and propose tNTK as a tractable kernel that captures sensitivity of the predicted distribution to model parameters. Using tNTK as a Gaussian process covariance, they greedily select inputs that minimize posterior variance, and demonstrate that this distribution‑aware strategy outperforms mean‑based NTK baselines across several generative model types and datasets.