Embedding Probability Distributions into Low Dimensional ℓ_1: Tree Ising Models via Truncated Metrics
arxiv(2023)
摘要
Given an arbitrary set of high dimensional points in ℓ_1, there are
known negative results that preclude the possibility of always mapping them to
a low dimensional ℓ_1 space while preserving distances with small
multiplicative distortion. This is in stark contrast with dimension reduction
in Euclidean space (ℓ_2) where such mappings are always possible. While
the first non-trivial lower bounds for ℓ_1 dimension reduction were
established almost 20 years ago, there has been limited progress in
understanding what sets of points in ℓ_1 are conducive to a
low-dimensional mapping.
In this work, we study a new characterization of ℓ_1 metrics that are
conducive to dimension reduction in ℓ_1. Our characterization focuses on
metrics that are defined by the disagreement of binary variables over a
probability distribution – any ℓ_1 metric can be represented in this
form. We show that, for configurations of n points in ℓ_1 obtained from
tree Ising models, we can reduce dimension to polylog(n) with
constant distortion. In doing so, we develop technical tools for embedding
truncated metrics which have been studied because of their applications in
computer vision, and are objects of independent interest in metric geometry.
Among other tools, we show how any ℓ_1 metric can be truncated with O(1)
distortion and O(log(n)) blowup in dimension.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要