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 2502.01265cs.LGcs.DS
收藏

关于d-单调函数的精确学习

On Exact Learning of $d$-Monotone Functions

Technion(以色列理工学院)

Nader H. Bshouty

AI总结:

本文研究有限格上d-单调布尔函数的精确学习问题,通过成员查询和等价查询给出时间复杂度上界,并证明在d为常数或各单调DNF规模为常数且d=O(log n)时可在多项式时间内学习。

摘要:

本文研究布尔类d-单调函数f:X→{0,1}在成员查询和等价查询下的可学习性,其中(X,≤)是一个有限格。我们证明,表示为f=F(g_1,g_2,…,g_d)形式的d-单调函数类,其中F是任意布尔函数F:{0,1}^d→{0,1},g_1,…,g_d:X→{0,1}是任意单调函数,其学习时间复杂度为σ(X)·(size(f)/d+1)^d,其中σ(X)是格X中从最大元素到最小元素的链上直接前驱数量的最大和,size(f)=size(g_1)+…+size(g_d),其中size(g_i)是g_i^{-1}(1)中极小元素的数量。对于布尔函数f:{0,1}^n→{0,1},表示为f=F(g_1,g_2,…,g_d)形式的d-单调函数类,其中F是任意布尔函数,g_1,…,g_d是任意单调DNF,其学习时间复杂度为O(n^2)·(size(f)/d+1)^d,其中size(f)=size(g_1)+…+size(g_d)。特别地,当d为常数时,该类可在多项式时间内学习。此外,当所有i的size(g_i)为常数且d=O(log n)时,该类也可在多项式时间内学习。

英文摘要:

In this paper, we study the learnability of the Boolean class of $d$-monotone functions $f:{\cal X}\to\{0,1\}$ from membership and equivalence queries, where $({\cal X},\le)$ is a finite lattice. We show that the class of $d$-monotone functions that are represented in the form $f=F(g_1,g_2,\ldots,g_d)$, where $F$ is any Boolean function $F:\{0,1\}^d\to\{0,1\}$ and $g_1,\ldots,g_d:{\cal X}\to \{0,1\}$ are any monotone functions, is learnable in time $σ({\cal X})\cdot (size(f)/d+1)^{d}$ where $σ({\cal X})$ is the maximum sum of the number of immediate predecessors in a chain from the largest element to the smallest element in the lattice ${\cal X}$ and $size(f)=size(g_1)+\cdots+size(g_d)$, where $size(g_i)$ is the number of minimal elements in $g_i^{-1}(1)$. For the Boolean function $f:\{0,1\}^n\to\{0,1\}$, the class of $d$-monotone functions that are represented in the form $f=F(g_1,g_2,\ldots,g_d)$, where $F$ is any Boolean function and $g_1,\ldots,g_d$ are any monotone DNF, is learnable in time $O(n^2)\cdot (size(f)/d+1)^{d}$ where $size(f)=size(g_1)+\cdots+size(g_d)$. In particular, this class is learnable in polynomial time when $d$ is constant. Additionally, this class is learnable in polynomial time when $size(g_i)$ is constant for all $i$ and $d=O(\log n)$.

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。

↑