Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhu, Yuchen, Chen, Tianrong, Kong, Lingkai, Theodorou, Evangelos A., Tao, Molei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913686331850752
author Zhu, Yuchen
Chen, Tianrong
Kong, Lingkai
Theodorou, Evangelos A.
Tao, Molei
author_facet Zhu, Yuchen
Chen, Tianrong
Kong, Lingkai
Theodorou, Evangelos A.
Tao, Molei
contents The generative modeling of data on manifolds is an important task, for which diffusion models in flat spaces typically need nontrivial adaptations. This article demonstrates how a technique called `trivialization' can transfer the effectiveness of diffusion models in Euclidean spaces to Lie groups. In particular, an auxiliary momentum variable was algorithmically introduced to help transport the position variable between data distribution and a fixed, easy-to-sample distribution. Normally, this would incur further difficulty for manifold data because momentum lives in a space that changes with the position. However, our trivialization technique creates a new momentum variable that stays in a simple fixed vector space. This design, together with a manifold preserving integrator, simplifies implementation and avoids inaccuracies created by approximations such as projections to tangent space and manifold, which were typically used in prior work, hence facilitating generation with high-fidelity and efficiency. The resulting method achieves state-of-the-art performance on protein and RNA torsion angle generation and sophisticated torus datasets. We also, arguably for the first time, tackle the generation of data on high-dimensional Special Orthogonal and Unitary groups, the latter essential for quantum problems. Code is available at https://github.com/yuchen-zhu-zyc/TDM.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16381
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
Zhu, Yuchen
Chen, Tianrong
Kong, Lingkai
Theodorou, Evangelos A.
Tao, Molei
Machine Learning
Artificial Intelligence
The generative modeling of data on manifolds is an important task, for which diffusion models in flat spaces typically need nontrivial adaptations. This article demonstrates how a technique called `trivialization' can transfer the effectiveness of diffusion models in Euclidean spaces to Lie groups. In particular, an auxiliary momentum variable was algorithmically introduced to help transport the position variable between data distribution and a fixed, easy-to-sample distribution. Normally, this would incur further difficulty for manifold data because momentum lives in a space that changes with the position. However, our trivialization technique creates a new momentum variable that stays in a simple fixed vector space. This design, together with a manifold preserving integrator, simplifies implementation and avoids inaccuracies created by approximations such as projections to tangent space and manifold, which were typically used in prior work, hence facilitating generation with high-fidelity and efficiency. The resulting method achieves state-of-the-art performance on protein and RNA torsion angle generation and sophisticated torus datasets. We also, arguably for the first time, tackle the generation of data on high-dimensional Special Orthogonal and Unitary groups, the latter essential for quantum problems. Code is available at https://github.com/yuchen-zhu-zyc/TDM.
title Trivialized Momentum Facilitates Diffusion Generative Modeling on Lie Groups
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2405.16381