提出新评估方法，更好测试采样器处理多模态的能力
Improving the evaluation of samplers on multi-modal targets
- 设计合成实验环境，系统评估采样器对多模态的适应性
- 重点考察采样器恢复各模态重要性的能力，这是关键难点
- 适用于研究生成模型采样机制的学者与算法开发者
解决多模态问题构成了采样技术的核心挑战之一。本文倡导对采样器进行更系统的评估，重点关注模式分离与维度这两个主要困难。为此，我们提出一种合成实验设置，并在若干采样器上进行验证，特别聚焦于恢复模态相对重要性的挑战性指标。此类评估对于诊断采样器处理多模态的潜力至关重要，有助于推动该领域的发展。
原文摘要 · Abstract (English)
Addressing multi-modality constitutes one of the major challenges of sampling. In this reflection paper, we advocate for a more systematic evaluation of samplers towards two sources of difficulty that are mode separation and dimension. For this, we propose a synthetic experimental setting that we illustrate on a selection of samplers, focusing on the challenging criterion of recovery of the mode relative importance. These evaluations are crucial to diagnose the potential of samplers to handle multi-modality and therefore to drive progress in the field.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。