Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing

• URL: http://arxiv.org/abs/2605.16520v1
• Date: Fri, 15 May 2026 18:14:38 GMT
• Title: Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing
• Abstract summary: Sampling-based Dual optimization (SBO) has achieved many successes in solving non-asymptotic problems without diffusion.<n>In this paper, we establish a non-asymptotic convergence analysis for SBO through a score of smoothing.<n>We propose an SBO algorithm, Diffusion-Inspired Annealing (DIDA), which is provably convergent to the global optimum.
• Score: 13.780989664925258
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sampling-based optimization (SBO), like cross-entropy method and evolutionary algorithms, has achieved many successes in solving non-convex problems without gradients, yet its convergence is poorly understood. In this paper, we establish a non-asymptotic convergence analysis for SBO through the lens of smoothing. Specifically, we recast SBO as gradient descent on a smoothed objective, mirroring noise-conditioned score ascent in diffusion models. Our first contribution is a landscape analysis of the smoothed objective, demonstrating how smoothing helps escape local minima and uncovering a fundamental coverage-optimality trade-off: smoothing renders the landscape more benign by enlarging the locally convex region around the global minimizer, but at the cost of introducing an optimality gap. Building on this insight, we establish non-asymptotic convergence guarantees for SBO algorithms to a neighborhood of the global minimizer. Furthermore, we propose an annealed SBO algorithm, Diffusion-Inspired Dual-Annealing (DIDA), which is provably convergent to the global optimum. We conduct extensive numerical experiments to verify our landscape results and also demonstrate the compelling performance of DIDA compared to other gradient-free optimization methods. Lastly, we discuss implications of our results for diffusion models.

Related papers

• Fitting Unknown Number of Hyperplanes with Manifold Optimization [57.48093263119306]
  Fitting unknown number of linearplanes to data is a fundamental yet challenging problem in machine learning.<n>Existing approaches often struggle with optimum optima or lack geometric consistency.
  arXiv  Detail & Related papers  (2026-05-27T14:02:20Z)
• Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization [66.08522228989634]
  We establish the first global convergence result of neural networks for two stage least squares (2SLS) approach in nonparametric instrumental variable regression (NPIV)<n>This is achieved by adopting a lifted perspective through mean-field Langevin dynamics (MFLD)
  arXiv  Detail & Related papers  (2025-11-18T17:51:17Z)
• Divergence Minimization Preference Optimization for Diffusion Model Alignment [66.31417479052774]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>DMPO can consistently outperform or match existing techniques across different base models and test sets.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Stochastic Optimization with Optimal Importance Sampling [49.484190237840714]
  We propose an iterative-based algorithm that jointly updates the decision and the IS distribution without requiring time-scale separation between the two.<n>Our method achieves the lowest possible variable variance and guarantees global convergence under convexity of the objective and mild assumptions on the IS distribution family.
  arXiv  Detail & Related papers  (2025-04-04T16:10:18Z)
• Gradient Normalization Provably Benefits Nonconvex SGD under Heavy-Tailed Noise [60.92029979853314]
  We investigate the roles of gradient normalization and clipping in ensuring the convergence of Gradient Descent (SGD) under heavy-tailed noise. Our work provides the first theoretical evidence demonstrating the benefits of gradient normalization in SGD under heavy-tailed noise. We introduce an accelerated SGD variant incorporating gradient normalization and clipping, further enhancing convergence rates under heavy-tailed noise.
  arXiv  Detail & Related papers  (2024-10-21T22:40:42Z)
• Dynamic Anisotropic Smoothing for Noisy Derivative-Free Optimization [0.0]
  We propose a novel algorithm that extends the methods of ball smoothing and Gaussian smoothing for noisy derivative-free optimization. The algorithm dynamically adapts the shape of the smoothing kernel to approximate the Hessian of the objective function around a local optimum.
  arXiv  Detail & Related papers  (2024-05-02T21:04:20Z)
• Proximal Oracles for Optimization and Sampling [18.77973093341588]
  We consider convex optimization with non-smooth objective function and log-concave sampling with non-smooth potential.<n>To overcome the challenges caused by non-smoothness, our algorithms employ two powerful proximal frameworks in optimization and sampling.
  arXiv  Detail & Related papers  (2024-04-02T18:52:28Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• ProGO: Probabilistic Global Optimizer [9.772380490791635]
  In this paper we develop an algorithm that converges to the global optima under some mild conditions. We show that the proposed algorithm outperforms, by order of magnitude, many existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-10-04T22:23:40Z)
• Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives [1.7640556247739623]
  We analyze algorithms for zeroth-order entropy composite objectives, focusing on dependence on dimensionality. This is achieved by exploiting low dimensional structure of the decision set using the mirror descent method with an estimation alike function. To improve the gradient, we replace the classic sampling method based on Rademacher and show that the mini-batch method copes with non-Eucli geometry.
  arXiv  Detail & Related papers  (2022-08-09T07:36:25Z)
• Differentiable Annealed Importance Sampling and the Perils of Gradient Noise [68.44523807580438]
  Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation. Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective. We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
  arXiv  Detail & Related papers  (2021-07-21T17:10:14Z)
• 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)
• An adaptive stochastic gradient-free approach for high-dimensional blackbox optimization [0.0]
  We propose an adaptive gradient-free (ASGF) approach for high-dimensional non-smoothing problems. We illustrate the performance of this method on benchmark global problems and learning tasks.
  arXiv  Detail & Related papers  (2020-06-18T22:47:58Z)

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.