GLENS: Global Search via Learning from Solver Iterates with Diffusion Models

• URL: http://arxiv.org/abs/2606.00366v1
• Date: Fri, 29 May 2026 21:09:56 GMT
• Title: GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
• Abstract summary: We consider the problem of generating a large collection of initial guesses for local minima non- continuous optimization problems.<n>We propose GLENS, a data-efficient global search method that leverages intermediate solvers as data.
• Score: 1.7495196015896808
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of generating a large collection of initial guesses for local minima of multimodal non-convex continuous optimization problems. The goal is for these initial guesses to be high-quality (i.e., a numerical solver converges quickly) and diverse (i.e., represent many different local minima). Identifying multiple locally optimal solutions enables flexible downstream decision-making, but typically requires expensive global search. Existing data-driven methods predict initial guesses using only the final converged optima from offline solver runs, which discards information about the local neighborhoods of solutions and limits the available training data. We propose GLENS (Global Search via Learning from Solver Iterates), a data-efficient global search method that leverages intermediate solver iterates as free data augmentation. GLENS consists of two components: a neighborhood structure model that uses diffusion models to learn the local geometry around optima conditioned on problem parameters, and a solver behavior model that learns refinement directions to further guide samples towards nearby optima during diffusion sampling. Experiments on modified non-convex benchmark problems and a two-robot obstacle-avoidance navigation problem show that GLENS generates high-quality initial guesses while preserving the multimodal distribution of diverse local optima. The resulting initial guesses lead to faster solver convergence across different problem settings and solvers. We also analyze how key hyperparameter choices affect the performance.

Related papers

• Complexity Bounds and Approaches to Learning Projected Gradient Descent Solver Iterates [0.3093890460224435]
  We study a $k$-neighborhood data collection strategy that augments datasets of converged solutions with intermediate solver iterates.<n>We propose a more capable DDDAS paradigm by improving the efficiency of the data-model-optimization loop.<n>We finish by discussing two views of learning solver-iterate data and connect our analysis with GLENS, a new data-efficient global search method.
  arXiv  Detail & Related papers  (2026-07-24T16:31:30Z)
• Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching [66.39914384073145]
  We propose a self-consistency framework that turns cheap diffusion-sampled reasoning into a reusable pool of step-level candidates.<n>We find that step-level recombination is most beneficial on harder problems.<n>Our training-free framework improves average accuracy by up to 2 across six math and coding tasks.
  arXiv  Detail & Related papers  (2026-02-26T11:08:39Z)
• Global Search for Optimal Low Thrust Spacecraft Trajectories using Diffusion Models and the Indirect Method [0.0]
  Long time-duration low-thrust nonlinear optimal spacecraft trajectory global search is a computationally and time expensive problem.<n>Generative machine learning models can be trained to learn how the solution structure varies with respect to a conditional parameter.<n>State-of-the-art diffusion models are integrated with the indirect approach for trajectory optimization within a global search framework.
  arXiv  Detail & Related papers  (2025-01-13T01:49:17Z)
• Global Search of Optimal Spacecraft Trajectories using Amortization and Deep Generative Models [0.5898893619901381]
  We formulate the parameterized global search problem as the task of sampling a conditional probability distribution with support on the neighborhoods of local basins of attraction to the high quality solutions.<n>The approach is benchmarked on a low thrust spacecraft trajectory optimization problem in the circular restricted three-body problem.<n>The paper also provides an in-depth analysis of the multi-modal funnel structure of a low-thrust spacecraft trajectory optimization problem.
  arXiv  Detail & Related papers  (2024-12-28T04:57:12Z)
• DiffSG: A Generative Solver for Network Optimization with Diffusion Model [75.27274046562806]
  Generative diffusion models are popular in various cross-domain applications.<n>These models hold promise in tackling complex network optimization problems.<n>We propose a new framework for generative diffusion models called Diffusion Model-based Solution Generation.
  arXiv  Detail & Related papers  (2024-08-13T07:56:21Z)
• DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimization [9.28162057044835]
  Optimal trajectory local is computationally expensive for nonlinear and high-dimensional dynamical systems. In this paper we introduce Diffu-based general model for non-dimensional optima problems. We also present Diff+, a novel constrained diffusion model with an additional loss in that further reduces the problem violations.
  arXiv  Detail & Related papers  (2024-02-22T03:52:17Z)
• Convex Relaxations of ReLU Neural Networks Approximate Global Optima in Polynomial Time [45.72323731094864]
  In this paper, we study the optimality gap between two-layer ReLULU networks regularized with weight decay and their convex relaxations. Our study sheds new light on understanding why local methods work well.
  arXiv  Detail & Related papers  (2024-02-06T01:29:35Z)
• Factorization of Multi-Agent Sampling-Based Motion Planning [72.42734061131569]
  Modern robotics often involves multiple embodied agents operating within a shared environment. Standard sampling-based algorithms can be used to search for solutions in the robots' joint space. We integrate the concept of factorization into sampling-based algorithms, which requires only minimal modifications to existing methods. We present a general implementation of a factorized SBA, derive an analytical gain in terms of sample complexity for PRM*, and showcase empirical results for RRG.
  arXiv  Detail & Related papers  (2023-04-01T15:50:18Z)
• Learning To Dive In Branch And Bound [95.13209326119153]
  We propose L2Dive to learn specific diving structurals with graph neural networks. We train generative models to predict variable assignments and leverage the duality of linear programs to make diving decisions.
  arXiv  Detail & Related papers  (2023-01-24T12:01:45Z)
• Learning Proximal Operators to Discover Multiple Optima [66.98045013486794]
  We present an end-to-end method to learn the proximal operator across non-family problems. We show that for weakly-ized objectives and under mild conditions, the method converges globally.
  arXiv  Detail & Related papers  (2022-01-28T05:53:28Z)
• Memory Clustering using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-starts [24.576214898129823]
  Shooting methods are an efficient approach to solving nonlinear optimal control problems. Recent work has focused on providing an initial guess from a learned model trained on samples generated during an offline exploration of the problem space. In this work, we apply tools from algebraic topology to extract information on the underlying structure of the solution space.
  arXiv  Detail & Related papers  (2020-10-02T14:24:59Z)
• Hardness of Random Optimization Problems for Boolean Circuits, Low-Degree Polynomials, and Langevin Dynamics [78.46689176407936]
  We show that families of algorithms fail to produce nearly optimal solutions with high probability. For the case of Boolean circuits, our results improve the state-of-the-art bounds known in circuit complexity theory.
  arXiv  Detail & Related papers  (2020-04-25T05:45:59Z)

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.