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 2307.07679stat.MLcs.LGcs.NAmath.NA
收藏

匹配追踪的锐利收敛速率

Sharp Convergence Rates for Matching Pursuit

Princeton University(普林斯顿大学);Texas A&M University(德克萨斯农工大学)

Jason M. Klusowski, Jonathan W. Siegel

AI总结:

本文研究了匹配追踪算法逼近目标函数的收敛速率,通过构建最坏情况字典弥合了误差上下界的差距,证明其收敛速率$n^{-α}$($α\approx 0.182$)是次优的。

摘要:

我们研究了匹配追踪(matching pursuit),或称纯贪婪算法(pure greedy algorithm),在通过字典中$n$个元素的线性组合$f_n$来逼近目标函数$f$时的基本极限。当目标函数包含在与该字典对应的变分空间中时,过去几十年中许多杰出的工作已经获得了匹配追踪误差$\\|f-f_n\\|$的上下界,但它们并不匹配。本文的主要贡献是弥合这一差距,并获得匹配追踪衰减率$n^{-α}$的锐利刻画。具体而言,我们构建了一个最坏情况字典,表明现有的最佳上界无法被显著改善。结果表明,与以最优速率$n^{-1/2}$收敛的其他贪婪算法变体不同,收敛速率$n^{-α}$是次优的。这里,$α\approx 0.182$由某个非线性方程的解确定。

英文摘要:

We study the fundamental limits of matching pursuit, or the pure greedy algorithm, for approximating a target function $ f $ by a linear combination $f_n$ of $n$ elements from a dictionary. When the target function is contained in the variation space corresponding to the dictionary, many impressive works over the past few decades have obtained upper and lower bounds on the error $\|f-f_n\|$ of matching pursuit, but they do not match. The main contribution of this paper is to close this gap and obtain a sharp characterization of the decay rate, $n^{-α}$, of matching pursuit. Specifically, we construct a worst case dictionary which shows that the existing best upper bound cannot be significantly improved. It turns out that, unlike other greedy algorithm variants which converge at the optimal rate $ n^{-1/2}$, the convergence rate $n^{-α}$ is suboptimal. Here, $α\approx 0.182$ is determined by the solution to a certain non-linear equation.

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。

↑