e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration

• URL: http://arxiv.org/abs/2502.02628v1
• Date: Tue, 04 Feb 2025 16:17:22 GMT
• Title: e-SimFT: Alignment of Generative Models with Simulation Feedback for Pareto-Front Design Exploration
• Authors: Hyunmin Cheong, Mohammadmehdi Ataei, Amir Hosein Khasahmadi, Pradeep Kumar Jayaraman,
• Abstract summary: We introduce a new framework for design exploration with simulation fine-tuned generative models. First, the framework adopts preference alignment methods developed for Large Language Models (LLMs) and showcases the first application in fine-tuning a generative model for engineering design.
• Score: 6.085974259020175
• License:
• Abstract: Deep generative models have recently shown success in solving complex engineering design problems where models predict solutions that address the design requirements specified as input. However, there remains a challenge in aligning such models for effective design exploration. For many design problems, finding a solution that meets all the requirements is infeasible. In such a case, engineers prefer to obtain a set of Pareto optimal solutions with respect to those requirements, but uniform sampling of generative models may not yield a useful Pareto front. To address this gap, we introduce a new framework for Pareto-front design exploration with simulation fine-tuned generative models. First, the framework adopts preference alignment methods developed for Large Language Models (LLMs) and showcases the first application in fine-tuning a generative model for engineering design. The important distinction here is that we use a simulator instead of humans to provide accurate and scalable feedback. Next, we propose epsilon-sampling, inspired by the epsilon-constraint method used for Pareto-front generation with classical optimization algorithms, to construct a high-quality Pareto front with the fine-tuned models. Our framework, named e-SimFT, is shown to produce better-quality Pareto fronts than existing multi-objective alignment methods.

Related papers

• Deep Generative Model for Mechanical System Configuration Design [3.2194137462952126]
  We propose a deep generative model to predict the optimal combination of components and interfaces for a given design problem. We then train a Transformer using this dataset, named GearFormer, which can generate quality solutions on its own. We show that GearFormer outperforms search methods on their own in terms of satisfying the specified design requirements.
  arXiv  Detail & Related papers  (2024-09-09T19:15:45Z)
• Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models [54.132297393662654]
  We introduce a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. We demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models.
  arXiv  Detail & Related papers  (2024-05-30T03:57:29Z)
• Diffusion Model for Data-Driven Black-Box Optimization [54.25693582870226]
  We focus on diffusion models, a powerful generative AI technology, and investigate their potential for black-box optimization. We study two practical types of labels: 1) noisy measurements of a real-valued reward function and 2) human preference based on pairwise comparisons. Our proposed method reformulates the design optimization problem into a conditional sampling problem, which allows us to leverage the power of diffusion models.
  arXiv  Detail & Related papers  (2024-03-20T00:41:12Z)
• Compositional Generative Inverse Design [69.22782875567547]
  Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem. We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples. In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
  arXiv  Detail & Related papers  (2024-01-24T01:33:39Z)
• Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation [17.164961143132473]
  We introduce a learning framework that demonstrates the efficacy of aligning the sampling trajectory of diffusion models with the optimization trajectory derived from traditional physics-based methods. Our method allows for generating feasible and high-performance designs in as few as two steps without the need for expensive preprocessing, external surrogate models, or additional labeled data. Our results demonstrate that TA outperforms state-of-the-art deep generative models on in-distribution configurations and halves the inference computational cost.
  arXiv  Detail & Related papers  (2023-05-29T09:16:07Z)
• XVoxel-Based Parametric Design Optimization of Feature Models [11.32057097341898]
  This paper introduces a new method for parametric optimization based on a unified model representation scheme called XVoxels. The presented method has been validated by a series of case studies of increasing complexity to demonstrate its effectiveness.
  arXiv  Detail & Related papers  (2023-03-17T13:07:12Z)
• A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences [55.25331349436895]
  Deep generative models have emerged as a popular machine learning-based approach for inverse problems in the life sciences. These problems often require sampling new designs that satisfy multiple properties of interest in addition to learning the data distribution.
  arXiv  Detail & Related papers  (2022-10-19T19:04:45Z)
• Designing MacPherson Suspension Architectures using Bayesian Optimization [21.295015276123962]
  Testing for compliance is performed first by computer simulation using a discipline model. Designs passing this simulation are then considered for physical prototyping. We show that the proposed approach is general, scalable, and efficient.
  arXiv  Detail & Related papers  (2022-06-17T21:50:25Z)
• Re-parameterizing Your Optimizers rather than Architectures [119.08740698936633]
  We propose a novel paradigm of incorporating model-specific prior knowledge into Structurals and using them to train generic (simple) models. As an implementation, we propose a novel methodology to add prior knowledge by modifying the gradients according to a set of model-specific hyper- parameters. For a simple model trained with a Repr, we focus on a VGG-style plain model and showcase that such a simple model trained with a Repr, which is referred to as Rep-VGG, performs on par with the recent well-designed models.
  arXiv  Detail & Related papers  (2022-05-30T16:55:59Z)
• Early-Phase Performance-Driven Design using Generative Models [0.0]
  This research introduces a novel method for performance-driven geometry generation that can afford interaction directly in the 3d modeling environment. The method uses Machine Learning techniques to train a generative model offline. By navigating the generative model's latent space, geometries with the desired characteristics can be quickly generated.
  arXiv  Detail & Related papers  (2021-07-19T01:25:11Z)
• Modeling the Second Player in Distributionally Robust Optimization [90.25995710696425]
  We argue for the use of neural generative models to characterize the worst-case distribution. This approach poses a number of implementation and optimization challenges. We find that the proposed approach yields models that are more robust than comparable baselines.
  arXiv  Detail & Related papers  (2021-03-18T14:26:26Z)

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.