PulseAugur
中
实时 07:56:01
English(EN) Non-Asymptotic Error Bounds for SMC with Biased Proposals: Application to Conditional Diffusion Sampling

新论文详细介绍了有偏差SMC采样器的非渐近误差界 · 跟踪3 个来源

作者 PulseAugur 编辑部 · [3 个来源] ·

一篇新论文介绍了在对序列蒙特卡洛（SMC）方法使用有偏差的变异核（在生成模型的后验条件中很常见）时的非渐近误差分析。该研究将总误差分解为核偏差和有限粒子蒙特卡洛误差，通过将马尔可夫核的条件扩展到条件分布，提供了一种控制偏差的原则性方法。该框架应用于基于分数的扩散模型，得出了第一个考虑了初始化、时间离散化、分数近似和粒子数量的非渐近误差界。 AI

影响 为通过先进的采样技术提高生成模型的准确性和可靠性提供了理论基础。

排序理由 该集群包含一篇学术论文，详细介绍了用于生成模型的新SMC方法理论框架和误差分析。

在 arXiv stat.ML 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新论文详细介绍了有偏差SMC采样器的非渐近误差界 · 跟踪3 个来源

报道来源 [3]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    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…

  2. 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…

  3. 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…

相关实体

相关话题