arXiv Machine Learning

Deep Multivariate Models with Parametric Conditionals

arXiv Machine Learning
Oct 19

Deep conditional distribution learning via conditional F\"ollmer flow

The paper presents Conditional Föllmer Flow, an ODE‑based deep generative approach for learning conditional distributions. Starting from a Gaussian, the flow approximates the target distribution near time 1, with Euler discretization and a neural‑network‑estimated velocity field. The authors prove convergence in Wasserstein‑2 distance and demonstrate superior performance on both nonparametric density estimation and image‑based tasks compared to existing methods.

By Jinyuan Chang, Zhao Ding, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang
arXiv Machine Learning
Oct 16

Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable model

The paper introduces a lightweight algorithm for modeling tabular data with both continuous and discrete variables. It transforms data into a continuous latent space using empirical marginals and a quantile function, enabling efficient estimation with distributions like a multivariate Gaussian. The method preserves complex marginal distributions and correlations, and handles discrete variables via a Monte Carlo expectation‑maximisation framework that allows conventional maximum‑likelihood estimation.

By Bartosz Barzdajn, Mateusz Krzyszto\'n
Hugging Face Trending Papers
Jun 29

UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception

Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.

arXiv Machine Learning
Jun 5

Zero-Flow Encoders

arXiv:2602. 00797v2 Announce Type: replace-cross Abstract: Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions.

By Yakun Wang, Leyang Wang, Song Liu, Taiji Suzuki
arXiv Machine Learning
Sep 25

Sufficiently Reduced Distributional Regression

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