6 citations · 7 across the 4 of their papers we have counts for
5 papers
Beyond ICA: Identifiability by Symmetry Breaking
Pengzhou Wu
We prove the identifiability of deep generative models (DGMs) with piecewise-affine (PWA) decoders and Gaussian mixture model (GMM) priors, in a purely unsupervised setting. We int…
Towards Principled Causal Effect Estimation by Deep Identifiable Models
Pengzhou Wu, Kenji Fukumizu
As an important problem in causal inference, we discuss the estimation of treatment effects (TEs). Representing the confounder as a latent variable, we propose Intact-VAE, a new va…
-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap
Pengzhou Wu, Kenji Fukumizu
As an important problem in causal inference, we discuss the identification and estimation of treatment effects (TEs) under limited overlap; that is, when subjects with certain feat…
Intact-VAE: Estimating Treatment Effects under Unobserved Confounding
Pengzhou Wu, Kenji Fukumizu
NOTE: This preprint has a flawed theoretical formulation. Please avoid it and refer to the ICLR22 publication https://openreview.net/forum?id=q7n2RngwOM. Also, arXiv:2109.15062 con…
Causal Mosaic: Cause-Effect Inference via Nonlinear ICA and Ensemble Method
Pengzhou Wu, Kenji Fukumizu
We address the problem of distinguishing cause from effect in bivariate setting. Based on recent developments in nonlinear independent component analysis (ICA), we train nonparamet…