基于自适应流采样的能量模型平衡训练
Balanced Training of Energy-Based Models with Adaptive Flow Sampling
AI总结：
提出一种利用normalizing flows辅助采样的EBMs最大似然训练新算法，通过训练时将NF拟合到EBM以提供准确梯度，最终实现快速生成新数据的采样器。
摘要：
能量模型（EBMs）是通用的密度估计模型，直接参数化未归一化的对数密度。尽管非常灵活，但EBMs缺乏模型指定的归一化常数，使得模型的似然在计算上难以处理。已经提出了几种近似采样器和变分推断技术来估计用于训练的似然梯度。这些技术在生成样本方面显示出有希望的结果，但很少关注估计密度的统计准确性，例如确定数据集中不同类别的相对重要性。在这项工作中，我们提出了一种新的用于EBMs的最大似然训练算法，该算法使用另一种类型的生成模型，即normalizing flows（NF），该模型最近被提出以促进采样。我们的方法在训练期间将NF拟合到EBM，以便NF辅助的采样方案始终为EBMs提供准确的梯度，最终产生用于生成新数据的快速采样器。
英文摘要：
Energy-based models (EBMs) are versatile density estimation models that directly parameterize an unnormalized log density. Although very flexible, EBMs lack a specified normalization constant of the model, making the likelihood of the model computationally intractable. Several approximate samplers and variational inference techniques have been proposed to estimate the likelihood gradients for training. These techniques have shown promising results in generating samples, but little attention has been paid to the statistical accuracy of the estimated density, such as determining the relative importance of different classes in a dataset. In this work, we propose a new maximum likelihood training algorithm for EBMs that uses a different type of generative model, normalizing flows (NF), which have recently been proposed to facilitate sampling. Our method fits an NF to an EBM during training so that an NF-assisted sampling scheme provides an accurate gradient for the EBMs at all times, ultimately leading to a fast sampler for generating new data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
