Score: 0

Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimization

Published: June 6, 2025 | arXiv ID: 2506.05680v1

By: Tailin Zhou , Zhilin Chen , Wenlong Lyu and more

Potential Business Impact:

Finds best designs even with unknown rules.

Business Areas:
Simulation Software

Optimizing complex systems, from discovering therapeutic drugs to designing high-performance materials, remains a fundamental challenge across science and engineering, as the underlying rules are often unknown and costly to evaluate. Offline optimization aims to optimize designs for target scores using pre-collected datasets without system interaction. However, conventional approaches may fail beyond training data, predicting inaccurate scores and generating inferior designs. This paper introduces ManGO, a diffusion-based framework that learns the design-score manifold, capturing the design-score interdependencies holistically. Unlike existing methods that treat design and score spaces in isolation, ManGO unifies forward prediction and backward generation, attaining generalization beyond training data. Key to this is its derivative-free guidance for conditional generation, coupled with adaptive inference-time scaling that dynamically optimizes denoising paths. Extensive evaluations demonstrate that ManGO outperforms 24 single- and 10 multi-objective optimization methods across diverse domains, including synthetic tasks, robot control, material design, DNA sequence, and real-world engineering optimization.

Country of Origin
🇭🇰 Hong Kong

Page Count
15 pages

Category
Computer Science:
Machine Learning (CS)