In this paper, we propose a novel uniform generalization bound on the time and inverse temperature for stochastic gradient Langevin dynamics (SGLD) in a non-convex setting. While previous works derive their generalization bounds by uniform stability, we use Rademacher complexity to make our generalization bound independent of the time and inverse temperature. Using Rademacher complexity, we can reduce the problem to derive a generalization bound on the whole space to that on a bounded region and therefore can remove the effect of the time and inverse temperature from our generalization bound. As an application of our generalization bound, an evaluation on the effectiveness of the simulated annealing in a non-convex setting is also described. For the sample size $n$ and time $s$, we derive evaluations with orders $\sqrt{n^{-1} \log (n+1)}$ and $|(\log)^4(s)|^{-1}$, respectively. Here, $(\log)^4$ denotes the $4$ times composition of the logarithmic function.
翻译:在本文中,我们建议对非碳化物环境中的随机梯度梯度动态的时间和反温进行新的统一归纳,对非碳化物环境中的时间和反温进行整合。虽然先前的工程通过统一稳定性得出其一般化界限,但我们使用Rademacher复杂度使我们的一般化不受时间和反温的影响。使用Rademacher复杂度,我们可以将问题缩小到对整个空间进行总体化,从而可以将时间和反温的影响从我们的一般化约束中去除。作为我们一般化约束的应用,还描述了对非碳化物环境中模拟的肛门效果的评估。对于样本大小,我们用美元和时间,我们用美元=qrt{n}-1}(n+1)}美元和 $ ⁇ (log)4 ⁇ (s)1}来进行评估。这里,美元(log)=4美元表示对正对数函数的4倍构成。