论文标题
EBM生命周期：MCMC合成，防御和密度建模策略
EBM Life Cycle: MCMC Strategies for Synthesis, Defense, and Density Modeling
论文作者
论文摘要
这项工作提出了根据其MCMC采样轨迹的期望长度学习基于能量的模型（EBM）的策略。不同长度的MCMC轨迹对应于具有不同目的的模型。我们的实验涵盖了三个不同的轨迹幅度和学习成果：1）图像产生的缩短抽样； 2）分类器 - 不足的对抗防御的中间抽样； 3）用于图像概率密度的原则建模的长抽样。为了实现这些结果，我们引入了三种新颖的MCMC初始化方法，用于最大似然（ML）学习中的负样本。借助标准网络体系结构和一个不变的ML目标，我们的MCMC初始化方法仅实现了我们研究的三个应用程序的大量性能提高。我们的结果包括CIFAR-10和Imagenet数据集中未归一化图像密度的最先进的FID得分；在纯化方法中，对CIFAR-10的最先进的对抗防御和ImageNet上的第一个EBM防御；以及可扩展的学习有效概率密度的技术。可以在https://github.com/point0bar1/ebm-life-cycle上找到该项目的代码。
This work presents strategies to learn an Energy-Based Model (EBM) according to the desired length of its MCMC sampling trajectories. MCMC trajectories of different lengths correspond to models with different purposes. Our experiments cover three different trajectory magnitudes and learning outcomes: 1) shortrun sampling for image generation; 2) midrun sampling for classifier-agnostic adversarial defense; and 3) longrun sampling for principled modeling of image probability densities. To achieve these outcomes, we introduce three novel methods of MCMC initialization for negative samples used in Maximum Likelihood (ML) learning. With standard network architectures and an unaltered ML objective, our MCMC initialization methods alone enable significant performance gains across the three applications that we investigate. Our results include state-of-the-art FID scores for unnormalized image densities on the CIFAR-10 and ImageNet datasets; state-of-the-art adversarial defense on CIFAR-10 among purification methods and the first EBM defense on ImageNet; and scalable techniques for learning valid probability densities. Code for this project can be found at https://github.com/point0bar1/ebm-life-cycle.
