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 1801.08499math.NAcs.NA
收藏

从高维点查询中学习通用稀疏加法模型

Learning general sparse additive models from point queries in high dimensions

INRIA Lille-Nord Europe(法国国家信息与自动化研究所里尔北欧中心);Alan Turing Institute(艾伦·图灵研究所);School of Mathematics, University of Edinburgh(爱丁堡大学数学学院);Dept. of Mathematics FNSPE, Czech Technical University in Prague(布拉格捷克技术大学应用科学与工程学院数学系)

Hemant Tyagi, Jan Vybiral

AI总结:

该研究提出了一种从高维点查询中学习稀疏加法模型的随机算法,通过精心构造的查询点精确恢复各阶交互项集合,无需依赖有限差分近似导数。

摘要:

我们考虑在立方体[-1,1]^d上定义的d元函数f的学习问题,其中算法假设具有该域内样本的黑盒访问权限。令S_r ⊂ [d] choose r; r=1,…,r_0表示由未知坐标变量的r阶交互组成的集合。我们聚焦于f具有加法结构的情况,即可以表示为f = ∑_{j∈S_1} ϕ_j + ∑_{j∈S_2} ϕ_j + … + ∑_{j∈S_{r_0}} ϕ_j,其中每个ϕ_j;j∈S_r最多为r元函数。我们推导出随机算法,通过精心构造的点集查询f,并以高概率精确恢复每个S_r。与先前工作不同,我们的分析不依赖于有限阶差分近似导数。

英文摘要:

We consider the problem of learning a $d$-variate function $f$ defined on the cube $[-1,1]^d\subset {\mathbb R}^d$, where the algorithm is assumed to have black box access to samples of $f$ within this domain. Denote ${\mathcal S}_r \subset {[d] \choose r}; r=1,\dots,r_0$ to be sets consisting of unknown $r$-wise interactions amongst the coordinate variables. We then focus on the setting where $f$ has an additive structure, i.e., it can be represented as $$f = \sum_{{\mathbf j} \in {\mathcal S}_1} ϕ_{\mathbf j} + \sum_{{\mathbf j} \in {\mathcal S}_2} ϕ_{\mathbf j} + \dots + \sum_{{\mathbf j} \in {\mathcal S}_{r_0}} ϕ_{\mathbf j},$$ where each $ϕ_{\mathbf j}$; ${\mathbf j} \in {\cal S}_r$ is at most $r$-variate for $1 \leq r \leq r_0$. We derive randomized algorithms that query $f$ at carefully constructed set of points, and exactly recover each ${\mathcal S}_r$ with high probability. In contrary to the previous work, our analysis does not rely on numerical approximation of derivatives by finite order differences.

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。

↑