Fast and Sample Near-Optimal Algorithms for Learning Multidimensional Histograms
(1802.08513)Abstract
We study the problem of robustly learning multi-dimensional histograms. A $d$-dimensional function $h: D \rightarrow \mathbb{R}$ is called a $k$-histogram if there exists a partition of the domain $D \subseteq \mathbb{R}d$ into $k$ axis-aligned rectangles such that $h$ is constant within each such rectangle. Let $f: D \rightarrow \mathbb{R}$ be a $d$-dimensional probability density function and suppose that $f$ is $\mathrm{OPT}$-close, in $L1$-distance, to an unknown $k$-histogram (with unknown partition). Our goal is to output a hypothesis that is $O(\mathrm{OPT}) + \epsilon$ close to $f$, in $L1$-distance. We give an algorithm for this learning problem that uses $n = \tilde{O}d(k/\epsilon2)$ samples and runs in time $\tilde{O}d(n)$. For any fixed dimension, our algorithm has optimal sample complexity, up to logarithmic factors, and runs in near-linear time. Prior to our work, the time complexity of the $d=1$ case was well-understood, but significant gaps in our understanding remained even for $d=2$.
We're not able to analyze this paper right now due to high demand.
Please check back later (sorry!).
Generate a summary of this paper on our Pro plan:
We ran into a problem analyzing this paper.