PulseAugur
实时 07:34:57
English(EN) Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

新论文详细介绍了具有偏差提议的SMC的非渐近误差界

一篇新论文介绍了在与有偏差提议一起使用时,序列蒙特卡洛(SMC)方法的非渐近误差分析。该研究由Stanislas Strasman撰写,将总误差分解为核偏差和有限粒子蒙特卡洛误差。该框架应用于基于分数的扩散模型的条件采样,提供了第一个考虑了初始化误差、时间离散化、分数近似和有限粒子误差的非渐近界。 AI

影响 为改进生成模型中的条件采样提供了理论框架,可能带来更准确可靠的AI输出。

排序理由 详细介绍新理论框架及其应用的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

新论文详细介绍了具有偏差提议的SMC的非渐近误差界

报道来源 [2]

  1. arXiv stat.ML TIER_1 English(EN) · Stanislas Strasman (SU, LPSM), Gabriel Victorino Cardoso (LPSM), Sylvain Le Corff (LPSM), Vincent Lemaire (LPSM), Antonio Ocello ·

    带偏见的提议的SMC的非渐近误差界:应用于条件扩散采样

    arXiv:2607.04780v1 Announce Type: new Abstract: Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynm…

  2. arXiv stat.ML TIER_1 English(EN) · Antonio Ocello ·

    具有偏差提议的SMC的非渐近误差界:应用于条件扩散采样

    Sequential Monte Carlo (SMC) methods are a natural tool for post-hoc conditioning of pretrained generative models, but in many applications the mutation kernels used by the particle system are biased approximations of an ideal Feynman--Kac flow. This paper develops a non-asymptot…