FROM LOW TO HIGH-VALUE DESIGNS: OFFLINE OPTIMIZATION VIA GENERALIZED DIFFUSION
Keywords: Diffusion Model, Probabilistic Method
TL;DR: We view offline optimization from the new lens of a distributional translation task which can be modeled with a generalized Brownian Bridge Diffusion process mapping between the low-value and high-value input distributions
Abstract: This paper studies the black-box optimization task which aims to find the maxima of a black-box function using only a static set of its observed input-output data. This is often achieved via learning and optimizing a surrogate function using such offline dataset. Alternatively, it can also be framed as an inverse modeling task which maps a desired performance to potential input candidates that achieve it. Both approaches are limited by the limited amount of offline data. To mitigate this limitation, we introduce a new perspective which casts offline optimization as a diffusion process mapping between an implicit distribution of low-value inputs (i.e., offline data) and a superior distribution of high-value inputs (i.e., solution candidates). Such diffusion process can be learned using low- and high-value inputs sampled from synthetic functions that resemble the target function. These synthetic functions are constructed as the mean posterior of multiple Gaussian processes fitted with different parameterizations on the offline data, alleviating the data bottleneck. Experimental results demonstrate that our approach consistently outperforms previous methods, establishing a new state-of-the-art performance.
Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 13300
Loading