[论文解读] Learning in Implicit Generative Models
本文将GANs置于广义的无似然、隐式生成建模范式中,并将密度比、假设检验以及跨相关方法的多重学习目标联系起来。
Generative adversarial networks (GANs) provide an algorithmic framework for constructing generative models with several appealing properties: they do not require a likelihood function to be specified, only a generating procedure; they provide samples that are sharp and compelling; and they allow us to harness our knowledge of building highly accurate neural network classifiers. Here, we develop our understanding of GANs with the aim of forming a rich view of this growing area of machine learning---to build connections to the diverse set of statistical thinking on this topic, of which much can be gained by a mutual exchange of ideas. We frame GANs within the wider landscape of algorithms for learning in implicit generative models--models that only specify a stochastic procedure with which to generate data--and relate these ideas to modelling problems in related fields, such as econometrics and approximate Bayesian computation. We develop likelihood-free inference methods and highlight hypothesis testing as a principle for learning in implicit generative models, using which we are able to derive the objective function used by GANs, and many other related objectives. The testing viewpoint directs our focus to the general problem of density ratio estimation. There are four approaches for density ratio estimation, one of which is a solution using classifiers to distinguish real from generated data. Other approaches such as divergence minimisation and moment matching have also been explored in the GAN literature, and we synthesise these views to form an understanding in terms of the relationships between them and the wider literature, highlighting avenues for future exploration and cross-pollination.
研究动机与目标
- 区分显式与隐式概率模型,并为复杂仿真器的隐式生成建模提供动机。
- 通过密度比较发展无似然推断,以在无可计算似然的隐式模型中进行学习。
- 通过假设检验和密度比估计来框定GAN及相关方法,以统一多种方法。
- 探讨基于分类的密度比、散度最小化以及矩/匹配技术之间的联系。
- 讨论评估、训练挑战,以及与ABC及相关框架的跨领域协同。
提出的方法
- 通过训练一个区分真实数据与生成数据的判别器来进行类别概率估计以计算密度比。
- 散度最小化(f-散度)及其变分形式用于引导学习。
- 比率匹配以及最小二乘/ Bregman 散度方法,用于估计密度比并驱动生成器学习。
- 矩匹配以及基于核的方法或MMD风格的目标,通过检验统计量比较分布。
- 双层优化,将比率(判别器)损失与生成器损失结合在一起,并考虑各种实际的损失函数选择与训练注意事项。
- 讨论替代损失(如Wasserstein)及其对梯度行为和训练稳定性的影响。
实验结果
研究问题
- RQ1通过比较真实数据和生成数据,在没有显式似然的情况下,如何在隐式生成模型中进行学习?
- RQ2在此背景下,类别概率估计、散度最小化、比率匹配和矩匹配之间有哪些关系?
- RQ3密度比如何作为核心工具(判别器)来引导推断与生成器优化?
- RQ4在隐式模型和GANs中,哪些有效的损失函数和训练策略可以稳定学习?
- RQ5这些方法如何与ABC及其他无似然框架的方法相关联并提供启示?
主要发现
- 通过分类器进行密度比估计提供了一种实用且核心的无似然学习机制,在隐式模型中。
- 散度最小化与类别概率估计是比较 p* 与 q 的同一框架的两面。
- 不同的损失族(伯努利、Brier、KL、f-散度)给出等价的不动点,但在训练动态和梯度上有所不同。
- 比率匹配和Bregman散度提供统一的视角,将GANs、f-GANs和LSIF风格的方法联系起来。
- 矩匹配和基于MMD的方法与密度比方法互为补充,并与ABC及最优传输等概念相关。
- 训练稳定性和梯度质量促使在标准GAN损失之外使用替代目标(如Wasserstein)。
更好的研究,从现在开始
从论文设计到论文写作,大幅缩短您的研究时间。
无需绑定信用卡
本解读由 AI 生成,并经人工编辑审核。