9 papers
Two-Sample Testing via Generative Processes
Eshant English, Kenji Fukumizu, Taiji Suzuki
Deciding whether two samples come from the same distribution is a classical problem in statistics, and generative transport offers a new way to approach it. We build a stochastic i…
Two-Sample Testing via Path-based Inference
Eshant English, Wei-Cheng Lai, Yanfeng Yang +3
Modern deep generative models are primarily studied for their ability to generate realistic samples, yet the generative dynamics they learn can also serve as objects of statistical…
Domain-Adapted Diffusion Models for Conditional Independence Testing
Yanfeng Yang, Junda Zhao, Yijie Gao +8
Conditional independence (CI) is a fundamental concept in statistics and machine learning. Recent advances in conditional generative modeling provide flexible tools for generative-…
Accelerated Dynamic Importance Weighting with Versatile Divergence-Minimizing Estimators
Tongtong Fang, Nan Lu, Gang Niu +2
Importance weighting (IW) is a golden solver for joint distribution shift, where the joint distributions differ between the training and test data. To solve this problem, IW estima…
Provably Learning Diffusion Models under the Manifold Hypothesis: Collapse and Refine
Wei Huang, Andi Han, Mingyuan Bai +4
Diffusion models generate high-dimensional data with remarkable quality, yet how training discovers and exploits low-dimensional manifold structure remains incompletely understood.…
Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
Shunyu Zhao, Yanfeng Yang, Shuai Li +1
Constraint-based causal discovery requires many conditional independence (CI) tests. Generative CI tests are attractive in nonlinear and high-dimensional settings because they can…
DoubleGen: Debiased Generative Modeling of Counterfactuals
Alex Luedtke, Kenji Fukumizu
Generative models for counterfactual outcomes face two key sources of bias. Confounding bias arises when approaches fail to account for systematic differences between those who rec…
Conditionally Whitened Generative Models for Probabilistic Time Series Forecasting
Yanfeng Yang, Siwei Chen, Pingping Hu +6
Probabilistic forecasting of multivariate time series is challenging due to non-stationarity, inter-variable dependencies, and distribution shifts. While recent diffusion and flow…
Diffusion Models with Double Guidance: Generate with aggregated datasets
Yanfeng Yang, Kenji Fukumizu
Creating large-scale datasets for training high-performance generative models is often prohibitively expensive, especially when associated attributes or annotations must be provide…