无需估计函数即可生成数据，基于粒子系统实现分布迁移。
Data Generation without Function Estimation
- 用确定性梯度下降更新点位置，实现分布转移
- 均场极限下可将均匀分布变为任意目标分布
- 无需训练、无噪声、无函数估计，适合理论研究
大多数生成模型的核心依赖于得分函数（或其它依赖种群密度的函数）的估计，但此类估计在计算和统计上均具挑战性。能否避免函数估计来生成数据？我们提出一种无需函数估计的生成方法：在均场极限下，一组通过（逆）梯度下降确定性更新的点，可将均匀分布传输至任意数据分布，无需函数估计、神经网络训练，甚至无需引入噪声。该方法基于相互作用粒子系统的最新物理进展，理论与实验均表明这些进展可被用于开发新型生成模型。
原文摘要 · Abstract (English)
Estimating the score function (or other population-density-dependent functions) is a fundamental component of most generative models. However, such function estimation is computationally and statistically challenging. Can we avoid function estimation for data generation? We propose an estimation-free generative method: A set of points whose locations are deterministically updated with (inverse) gradient descent can transport a uniform distribution to arbitrary data distribution, in the mean field regime, without function estimation, training neural networks, and even noise injection. The proposed method is built upon recent advances in the physics of interacting particles. We show, both theoretically and experimentally, that these advances can be leveraged to develop novel generative methods.
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。