arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2504.02544cs.LGcs.AI
收藏

用于多重集和测度的傅里叶切片-瓦瑟斯坦嵌入

Fourier Sliced-Wasserstein Embedding for Multisets and Measures

Tal Amir, Nadav Dym

AI总结:

该研究提出傅里叶切片-瓦瑟斯坦(FSW)嵌入方法,可将多重集和测度嵌入欧几里得空间,保留几何结构且具单射和双李普希茨特性,实验表明其在瓦瑟斯坦距离学习和提升PointNet鲁棒性上表现优异。

摘要:

我们提出了傅里叶切片-瓦瑟斯坦(FSW)嵌入——一种将$\mathbb{R}^d$上的多重集和测度嵌入到欧几里得空间的新方法。我们提出的嵌入近似保留了分布上的切片瓦瑟斯坦距离,从而产生更能捕捉输入结构的几何意义表示。此外,它在测度上是单射的,在多重集上是双李普希茨的——这是相对于基于求和或最大池化的流行方法的显著优势,后者被证明不是双李普希茨的,并且在许多情况下甚至不是单射的。这些保证所需的输出维度接近最优:大约为$2Nd$,其中$N$是最大输入多重集大小。此外,我们证明了不可能以双李普希茨方式将$\mathbb{R}^d$上的分布嵌入到欧几里得空间中。因此,我们的嵌入的度量性质在某种意义上是最佳可能的。通过数值实验,我们证明了我们的方法产生了更优的多重集表示,从而提高了实际学习任务中的性能。具体而言,我们表明:(a)FSW嵌入与MLP的简单组合在学习(非切片)瓦瑟斯坦距离方面达到了最先进的性能;(b)用FSW嵌入替换最大池化使PointNet对参数减少的鲁棒性显著提高,即使在40倍减少后也只有轻微的性能下降。

英文摘要:

We present the Fourier Sliced-Wasserstein (FSW) embedding - a novel method to embed multisets and measures over $\mathbb{R}^d$ into Euclidean space. Our proposed embedding approximately preserves the sliced Wasserstein distance on distributions, thereby yielding geometrically meaningful representations that better capture the structure of the input. Moreover, it is injective on measures and bi-Lipschitz on multisets - a significant advantage over prevalent methods based on sum- or max-pooling, which are provably not bi-Lipschitz, and, in many cases, not even injective. The required output dimension for these guarantees is near-optimal: roughly $2 N d$, where $N$ is the maximal input multiset size. Furthermore, we prove that it is impossible to embed distributions over $\mathbb{R}^d$ into Euclidean space in a bi-Lipschitz manner. Thus, the metric properties of our embedding are, in a sense, the best possible. Through numerical experiments, we demonstrate that our method yields superior multiset representations that improve performance in practical learning tasks. Specifically, we show that (a) a simple combination of the FSW embedding with an MLP achieves state-of-the-art performance in learning the (non-sliced) Wasserstein distance; and (b) replacing max-pooling with the FSW embedding makes PointNet significantly more robust to parameter reduction, with only minor performance degradation even after a 40-fold reduction.

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。

↑