We consider the problem of upper bounding the expected log-likelihood sub-optimality of the maximum likelihood estimate (MLE), or a conjugate maximum a posteriori (MAP) for an exponential family, in a non-asymptotic way. Surprisingly, we found no general solution to this problem in the literature. In particular, current theories do not hold for a Gaussian or in the interesting few samples regime. After exhibiting various facets of the problem, we show we can interpret the MAP as running stochastic mirror descent (SMD) on the log-likelihood. However, modern convergence results do not apply for standard examples of the exponential family, highlighting holes in the convergence literature. We believe solving this very fundamental problem may bring progress to both the statistics and optimization communities.
翻译:我们考虑的是将预期的日志可能性估计(MLE)的亚优化度上限化的问题,或者将指数型家庭(以非无损方式)的事后最大值(MAP)混为一谈的问题。令人惊讶的是,在文献中,我们没有找到解决这一问题的一般办法。特别是,目前的理论对高斯人或对少数有趣的样本体系来说都站不住脚。在展示了问题的各个方面之后,我们证明我们可以将MAP解释为对日志类家庭(SMD)的模拟镜底(SMD)运行。然而,现代趋同结果不适用于指数型家庭的标准例子,突出了趋同文献中的漏洞。我们认为,解决这一根本性问题可能会给统计界和优化社区带来进步。