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 2311.17840cs.DScs.LGstat.ML
收藏

通过 Sherali-Adams 超越双 Lipschitz 失真的度量嵌入

Metric Embeddings Beyond Bi-Lipschitz Distortion via Sherali-Adams

MIT(麻省理工学院);Google Research(谷歌研究院)

Ainesh Bakshi, Vincent Cohen-Addad, Samuel B. Hopkins, Rajesh Jayaram, Silvio Lattanzi

AI总结:

本文研究多维缩放(MDS)的可证近似算法,通过对 Sherali-Adams LP 层次结构进行几何感知的条件舍入,首次将输入相异度纵横比的依赖降至准多项式。

摘要:

度量嵌入是算法设计中广泛使用的方法,通常将一个“复杂”度量嵌入到更简单、更低维的度量中。历史上,理论计算机科学界关注双 Lipschitz 嵌入,这类嵌入保证每个成对距离都得到近似保持。相比之下,实践中常用的其他嵌入目标会避免双 Lipschitz 失真;然而这些方法在理论上受到的研究相对较少。本文聚焦多维缩放(MDS):给定 n 个点上的一组非负相异度 ${d_{i,j}}_{i,j\in [n]}$,目标是找到嵌入 $\{x_1,\dots,x_n\}\subset R^k$,使 $$\textrm{OPT}=\min_x\mathbb{E}_{i,j\in [n]}\left(1-\frac{\\|x_i-x_j\\|}{d_{i,j}}\right)^2$$ 最小。尽管 MDS 很流行,我们对其理论理解仍极其有限。最近,Demaine 等人(arXiv:2109.11505)给出该目标首个具有可证保证的近似算法,在常数维欧几里得空间中以 $n^2\cdot 2^{\textrm{poly}(\Delta/\varepsilon)}$ 时间获得代价为 $\textrm{OPT}+\varepsilon$ 的嵌入,其中 $\Delta$ 是输入相异度的纵横比。对于允许低成本嵌入的度量,$\Delta$ 随 n 呈多项式增长。本工作提出首个对 $\Delta$ 具有准多项式依赖的 MDS 近似算法:在常数维欧几里得空间中,以 $n^{O(1)}\cdot 2^{\text{poly}((\log(\Delta)/\varepsilon))}$ 时间获得代价为 $O(\log \Delta)\cdot \textrm{OPT}^{\Omega(1)}+\varepsilon$ 的解。我们的算法基于对 Sherali-Adams LP 层次结构条件舍入的新颖几何感知分析,使我们能够避免这种舍入通常会导致的对纵横比的指数依赖。

英文摘要:

Metric embeddings are a widely used method in algorithm design, where generally a ``complex'' metric is embedded into a simpler, lower-dimensional one. Historically, the theoretical computer science community has focused on bi-Lipschitz embeddings, which guarantee that every pairwise distance is approximately preserved. In contrast, alternative embedding objectives that are commonly used in practice avoid bi-Lipschitz distortion; yet these approaches have received comparatively less study in theory. In this paper, we focus on Multi-dimensional Scaling (MDS), where we are given a set of non-negative dissimilarities $\{d_{i,j}\}_{i,j\in [n]}$ over $n$ points, and the goal is to find an embedding $\{x_1,\dots,x_n\} \subset R^k$ that minimizes $$\textrm{OPT}=\min_{x}\mathbb{E}_{i,j\in [n]}\left(1-\frac{\|x_i - x_j\|}{d_{i,j}}\right)^2.$$ Despite its popularity, our theoretical understanding of MDS is extremely limited. Recently, Demaine et. al. (arXiv:2109.11505) gave the first approximation algorithm with provable guarantees for this objective, which achieves an embedding in constant dimensional Euclidean space with cost $\textrm{OPT} +ε$ in $n^2\cdot 2^{\textrm{poly}(Δ/ε)}$ time, where $Δ$ is the aspect ratio of the input dissimilarities. For metrics that admit low-cost embeddings, $Δ$ scales polynomially in $n$. In this work, we give the first approximation algorithm for MDS with quasi-polynomial dependency on $Δ$: for constant dimensional Euclidean space, we achieve a solution with cost $O(\log Δ)\cdot \textrm{OPT}^{Ω(1)}+ε$ in time $n^{O(1)} \cdot 2^{\text{poly}((\log(Δ)/ε))}$. Our algorithms are based on a novel geometry-aware analysis of a conditional rounding of the Sherali-Adams LP Hierarchy, allowing us to avoid exponential dependency on the aspect ratio, which would typically result from this rounding.

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。

↑