论文标题
有限V.S.的优势的经验分析无限宽度贝叶斯神经网络
An Empirical Analysis of the Advantages of Finite- v.s. Infinite-Width Bayesian Neural Networks
论文作者
论文摘要
比较具有不同宽度的贝叶斯神经网络（BNN）是具有挑战性的，因为随着宽度的增加，多个模型属性同时变化，并且在有限宽度的情况下进行了推断。在这项工作中，我们从经验上比较了有限和无限宽度的BNN，并为其性能差异提供了定量和定性的解释。我们发现，当模型被错误指定时，宽度的增加可能会损害BNN的性能。在这些情况下，我们提供的证据表明，由于其频谱的特性使它们能够在模型不匹配下适应其频谱的特性，因此有限宽度的BNN会更好地概括。
Comparing Bayesian neural networks (BNNs) with different widths is challenging because, as the width increases, multiple model properties change simultaneously, and, inference in the finite-width case is intractable. In this work, we empirically compare finite- and infinite-width BNNs, and provide quantitative and qualitative explanations for their performance difference. We find that when the model is mis-specified, increasing width can hurt BNN performance. In these cases, we provide evidence that finite-width BNNs generalize better partially due to the properties of their frequency spectrum that allows them to adapt under model mismatch.
