arXiv:2609.23789v1 Announce Type: new
Abstract: Modern conditional generative models face significant challenges when learning complex covariate dependencies. While sufficient dimension reduction (SD...
By Wenxi Tan, Bing Li, Lingzhou Xue
The paper introduces generalized engression models, a unified nonparametric framework for estimating the full conditional distribution of multivariate outcomes that may include continuous, binary, categorical, ordinal, or ranking variables. Building on the engression deep generative model, it incorporates data‑type‑specific link functions and a stochastic perturbation to smooth the loss, allowing gradient‑based training even with discontinuous links. The authors prove universal representation results for continuous, discrete, and mixed outcomes, and demonstrate that the method matches or surpasses existing type‑specific and joint species distribution models in simulations and two real‑world applications.
By Xinwei Shen, Zijian Guo, Francis Bach
arXiv:2607. 16725v1 Announce Type: cross Abstract: Conditional generative modeling remains a challenging problem in semi-supervised settings where labeled data is scarce but unlabeled samples are abundant.
By Changyu Liu, Yuling Jiao, Jian Huang
Sufficiently Reduced Distributional Regression (SRDR) is a generative approach that merges conditional distribution estimation with nonlinear sufficient dimension reduction (SDR). By framing SDR as a risk minimization problem using strictly proper scoring rules, SRDR jointly learns a dimension reduction map and a generative prediction model through minimization of the energy score, which can be estimated via sampling. The method extends to multi‑environment data and classification, and theoretical results show convergence of estimated conditional distributions in energy distance, implying asymptotic sufficiency. In experiments on CT slice localization, superconductivity data, and digit classification, SRDR recovers low‑dimensional sufficient structure and matches or surpasses state‑of‑the‑art nonlinear SDR methods in representation quality and predictive performance.
By Alexander Henzi, Tiange Liu, Xinwei Shen
arXiv:2603.20111v2 Announce Type: replace
Abstract: The Joint-Embedding Predictive Architecture (JEPA) is often seen as a non-generative alternative to likelihood-based self-supervised learning, emph...
By Moritz G\"ogl, Christopher Yau
arXiv:2607. 01275v1 Announce Type: cross Abstract: Variational Autoencoders (VAEs) commonly assume a standard isotropic Gaussian prior over the latent space, an assumption that often fails to capture the true distribution of latent representations for complex datasets.
By Qijun Chen, Shaofan Li
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.
By Shijin Gong, Baihua He, Xinyu Zhang
arXiv:2408. 15344v2 Announce Type: replace Abstract: Many scientific and engineering problems involve observing a common phenomenon through multiple heterogeneous sensors or measurement modalities.
By George A. Kevrekidis, Eleni D. Koronaki, Dimitris G. Giovanis, Yannis G. Kevrekidis
The Marformer is a Transformer model designed to predict conditional marginal distributions of missing variables given observed data, enabling computation of Bayes risk and Value of Information. It learns a hidden-vector representation for each variable’s distribution and refines these through attention, similar to BERT’s masked language modeling but for probabilistic inference. Evaluations on synthetic Bayesian networks, discretized Gaussians, structured annotation data, and a real annotation dataset show that the Marformer matches or surpasses classical missing-data methods while being faster and not requiring explicit joint distribution modeling.
By Prabhav Singh, Xiheng Tom Wang, Haojun Shi, Jason Eisner
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:2607. 08254v1 Announce Type: new Abstract: Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.
By Sai Spandana Chintapalli, Pratik Chaudhari, Christos Davatzikos
arXiv:2607. 23751v1 Announce Type: new Abstract: The usefulness of a variational autoencoder (VAE) depends on two properties of its latent space that are hard to obtain together: high encoding capacity in the individual latent variables, and a low-dimensional, disentangled organization of those variables.
By Ye Shi