重新思考生成模式覆盖：逐点保证方法
Rethinking Generative Mode Coverage: A Pointwise Guaranteed Approach
摘要：
许多生成模型必须与$\textit{missing modes}$作斗争。为此目的的传统智慧是通过训练来减小所生成的分布与所提供的数据分布之间的统计距离（诸如$f$-发散）。但这更多的是一种启发，而不是一种保证。统计距离测量两个分布之间的$\textit{global}$而不是$\textit{local}$相似性。即使它很小，它也不意味着一个合理的模式覆盖。重新思考这个问题，从博弈论的角度来看，我们表明，一个完整的模式覆盖是牢固地实现。如果生成模型可以在全局统计距离度量下适度地近似数据分布，那么我们将能够找到共同覆盖$\textit{every}$数据点的生成器的混合，从而覆盖$\textit{every}$模式，具有下界生成概率。构造生成器混合物与乘法权重更新规则有关，我们提出了我们的算法。我们证明，我们的算法保证完整的模式覆盖。我们在真实和合成数据集上的实验证实了比最近的方法更好的模式覆盖率，这些方法也使用生成器混合，但依赖于全局统计距离。
英文摘要：
Many generative models have to combat $\textit{missing modes}$. The conventional wisdom to this end is by reducing through training a statistical distance (such as $f$-divergence) between the generated distribution and provided data distribution. But this is more of a heuristic than a guarantee. The statistical distance measures a $\textit{global}$, but not $\textit{local}$, similarity between two distributions. Even if it is small, it does not imply a plausible mode coverage. Rethinking this problem from a game-theoretic perspective, we show that a complete mode coverage is firmly attainable. If a generative model can approximate a data distribution moderately well under a global statistical distance measure, then we will be able to find a mixture of generators that collectively covers $\textit{every}$ data point and thus $\textit{every}$ mode, with a lower-bounded generation probability. Constructing the generator mixture has a connection to the multiplicative weights update rule, upon which we propose our algorithm. We prove that our algorithm guarantees complete mode coverage. And our experiments on real and synthetic datasets confirm better mode coverage over recent approaches, ones that also use generator mixtures but rely on global statistical distances.
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。
