arXiv Machine Learning By HakGeun Lee, Hyonho Chun

Identifiability and Stability of Generative Drifting in the Companion-Elliptic Kernel Family

Read the original on arXiv Machine Learning →

arXiv:2604. 24196v4 Announce Type: replace-cross Abstract: A drifting model is a one-step generator trained by moving each sample along a field of kernel-weighted attraction toward data samples and repulsion between model samples; training halts once this field vanishes.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv AI
Aug 11

Second Order Drifting Models

arXiv:2608. 07924v1 Announce Type: cross Abstract: Drifting models are a recent class of one-step generative models that evolve the model distribution during training using a predefined sample-based drift field.

By Drake Brown, Yuhao Huang, Shih-Hsin Wang, Bao Wang
arXiv Machine Learning
Jun 30

Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

arXiv:2410. 01244v2 Announce Type: replace-cross Abstract: We introduce a novel Wasserstein-1 ($W_1$) path-space divergence for stochastic and deterministic dynamics and establish a Wasserstein Uncertainty Propagation (WUP) theorem that bounds the $W_1$ distance between terminal distributions by the proposed divergence, equivalently characterized by a weighted $L^2$ discrepancy between the underlying drifts and the $W_1$ distance between their initial measures.

By Ziyu Chen, Markos A. Katsoulakis, Benjamin J. Zhang