Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation
- URL: http://arxiv.org/abs/2406.00812v2
- Date: Sat, 8 Jun 2024 10:28:48 GMT
- Title: Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation
- Authors: Yueming Lyu, Kim Yong Tan, Yew Soon Ong, Ivor W. Tsang,
- Abstract summary: We show how to perform user-preferred targeted generation via diffusion models with only black-box target scores of users.
Experiments on both numerical test problems and target-guided 3D-molecule generation tasks show the superior performance of our method in achieving better target scores.
- Score: 60.41803046775034
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc. However, how to perform user-preferred targeted generation via diffusion models with only black-box target scores of users remains challenging. To address this issue, we first formulate the fine-tuning of the targeted reserve-time stochastic differential equation (SDE) associated with a pre-trained diffusion model as a sequential black-box optimization problem. Furthermore, we propose a novel covariance-adaptive sequential optimization algorithm to optimize cumulative black-box scores under unknown transition dynamics. Theoretically, we prove a $O(\frac{d^2}{\sqrt{T}})$ convergence rate for cumulative convex functions without smooth and strongly convex assumptions. Empirically, experiments on both numerical test problems and target-guided 3D-molecule generation tasks show the superior performance of our method in achieving better target scores.
Related papers
- Diff-BBO: Diffusion-Based Inverse Modeling for Black-Box Optimization [20.45482366024264]
Black-box optimization (BBO) aims to optimize an objective function by iteratively querying a black-box oracle.
diffusion models have demonstrated impressive capability in learning the high-dimensional data manifold.
We propose Diff-BBO, the first inverse approach leveraging diffusion models for online BBO problem.
arXiv Detail & Related papers (2024-06-30T06:58:31Z) - Variational Schrödinger Diffusion Models [14.480273869571468]
Schr"odinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models.
We leverage variational inference to linearize the forward score functions (variational scores) of SB.
We propose the variational Schr"odinger diffusion model (VSDM), where the forward process is a multivariate diffusion and the variational scores are adaptively optimized for efficient transport.
arXiv Detail & Related papers (2024-05-08T04:01:40Z) - Principled Preferential Bayesian Optimization [22.269732173306192]
We study the problem of preferential Bayesian optimization (BO)
We aim to optimize a black-box function with only preference feedback over a pair of candidate solutions.
An optimistic algorithm with an efficient computational method is then developed to solve the problem.
arXiv Detail & Related papers (2024-02-08T02:57:47Z) - Gaussian Mixture Solvers for Diffusion Models [84.83349474361204]
We introduce a novel class of SDE-based solvers called GMS for diffusion models.
Our solver outperforms numerous SDE-based solvers in terms of sample quality in image generation and stroke-based synthesis.
arXiv Detail & Related papers (2023-11-02T02:05:38Z) - Differentiating Metropolis-Hastings to Optimize Intractable Densities [51.16801956665228]
We develop an algorithm for automatic differentiation of Metropolis-Hastings samplers.
We apply gradient-based optimization to objectives expressed as expectations over intractable target densities.
arXiv Detail & Related papers (2023-06-13T17:56:02Z) - Protein Design with Guided Discrete Diffusion [67.06148688398677]
A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling.
We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models.
NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
arXiv Detail & Related papers (2023-05-31T16:31:24Z) - Conditional Denoising Diffusion for Sequential Recommendation [62.127862728308045]
Two prominent generative models, Generative Adversarial Networks (GANs) and Variational AutoEncoders (VAEs)
GANs suffer from unstable optimization, while VAEs are prone to posterior collapse and over-smoothed generations.
We present a conditional denoising diffusion model, which includes a sequence encoder, a cross-attentive denoising decoder, and a step-wise diffuser.
arXiv Detail & Related papers (2023-04-22T15:32:59Z) - Non-smooth Bayesian Optimization in Tuning Problems [5.768843113172494]
Building surrogate models is one common approach when we attempt to learn unknown black-box functions.
We propose a novel additive Gaussian process model called clustered Gaussian process (cGP), where the additive components are induced by clustering.
In the examples we studied, the performance can be improved by as much as 90% among repetitive experiments.
arXiv Detail & Related papers (2021-09-15T20:22:09Z) - Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box
Optimization Framework [100.36569795440889]
This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information.
We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
arXiv Detail & Related papers (2020-12-21T17:29:58Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.