{"ID":2865964,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21058","arxiv_id":"2509.21058","title":"SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion","abstract":"Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we introduce SPREAD, a generative framework based on Denoising Diffusion Probabilistic Models (DDPMs). SPREAD first learns a conditional diffusion process over points sampled from the decision space and then, at each reverse diffusion step, refines candidates via a sampling scheme that uses an adaptive multiple gradient descent-inspired update for fast convergence alongside a Gaussian RBF-based repulsion term for diversity. Empirical results on multi-objective optimization benchmarks, including offline and Bayesian surrogate-based settings, show that SPREAD matches or exceeds leading baselines in efficiency, scalability, and Pareto front coverage. Code is available at https://github.com/safe-autonomous-systems/moo-spread .","short_abstract":"Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for large-scale and expensive problems. To bridge this gap, we introduce SPREAD, a generative framework based on Denoising Diffusion Probabilistic...","url_abs":"https://arxiv.org/abs/2509.21058","url_pdf":"https://arxiv.org/pdf/2509.21058v2","authors":"[\"Sedjro Salomon Hotegni\",\"Sebastian Peitz\"]","published":"2025-09-25T12:09:37Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false,"code_links":[{"ID":609323,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2865964,"paper_url":"https://arxiv.org/abs/2509.21058","paper_title":"SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion","repo_url":"https://github.com/safe-autonomous-systems/moo-spread","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}