Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify probability density or mass functions up to an unknown normalizing constant. Unlike most other probabilistic models, EBMs do not place a restriction on the tractability of the normalizing constant, thus are more flexible to parameterize and can model a more expressive family of probability distributions. However, the unknown normalizing constant of EBMs makes training particularly difficult. Our goal is to provide a friendly introduction to modern approaches for EBM training. We start by explaining maximum likelihood training with Markov chain Monte Carlo (MCMC), and proceed to elaborate on MCMC-free approaches, including Score Matching (SM) and Noise Constrastive Estimation (NCE). We highlight theoretical connections among these three approaches, and end with a brief survey on alternative training methods, which are still under active research. Our tutorial is targeted at an audience with basic understanding of generative models who want to apply EBMs or start a research project in this direction.
翻译:以能源为基础的模型(EBMs)也称为非常规概率模型(EBMs ), 指定概率密度或质量函数, 直至未知的正常常数。 与大多数其他概率模型不同, EBM 不限制正常常数的可移动性, 因而更灵活地参数化, 并且可以模拟更清晰的概率分布模式。 然而, 未知的 EBM 常数使得培训特别困难。 我们的目标是为EBM 培训提供一种友好的现代方法介绍。 我们首先与Markov 链 Monte Carlo (MC ) 解释最大的可能性培训, 并着手详细介绍无MCMC 方法, 包括计分匹配和噪音分量刺激。 我们强调这三种方法之间的理论联系, 最后简要地调查替代培训方法,这些方法仍在积极研究中。 我们的辅导对象是那些对想要应用 EBMMBs 或在这方面启动研究项目的基因描述模型有基本理解的受众。