Searcharxiv⌕ Search

arXiv subjects

Liliia Redina

Publications and source records attributed to Liliia Redina.

2 recordsLinked to original sources

Local Modifications of Nearest-Neighbor and Min-Plus Representations

We study how changing a Boolean-valued function at $d$ inputs affects the size and precision of its exact representations. Starting from a representation of size $m$, we prove four bounds, two for nearest-neighbor (NN) representations and two for integer min-plus representations. (i) For NN representations on a finite subset of $\mathbb{R}^n$ with $n\ge2$, at most $m+2d$ anchors suffice. The coefficient $2$ is optimal: on a three-point domain, changing one value can increase the minimum number of anchors from one to three. (ii) For NN representations on the Boolean cube with rational anchors, let $R$ be the maximum original coordinate bit length, and let $Δ$ be the maximum bit length of the least common denominator of any one original anchor's coordinates. We construct a representation with at most $m+3d$ anchors on a common dyadic grid and coordinate bit length $O(R+Δ+\log(n+1))$. (iii) For integer min-plus representations on the Boolean cube, we give a construction that keeps the original $m$ forms and their labels and adds at most $d$ new forms. Its maximum weight is at most $W+2n$, where $W$ is the largest absolute original coefficient, including constant terms. (iv) For integer min-plus representations on a finite rational domain $X\subset\mathbb{Q}^n$, at most $m+2d$ forms suffice. Their maximum weight is polynomially bounded in $m,d,W,n,|X|$, the coordinate bound, and the common denominator of $X$. The coefficient $2$ is again optimal: on a three-point domain, changing one value can increase the minimum number of forms from one to three. These bounds imply stability under polynomially many changes on the cube for polynomial-size representations, including those with polynomially bounded NN coordinate bit length or min-plus weight.

cs.CC↗

A Faster Algorithm for Independent Cut

The previously fastest algorithm for deciding the existence of an independent cut had a runtime of $\mathcal{O}^*(1.4423^n)$, where $n$ is the order of the input graph. We improve this to $\mathcal{O}^*(1.4143^n)$. In fact, we prove a runtime of $\mathcal{O}^*\left( 2^{(\frac{1}{2}-α_Δ)n} \right)$ on graphs of order $n$ and maximum degree at most $Δ$, where $α_Δ=\frac{1}{2+4\lfloor \fracΔ{2} \rfloor}$. Furthermore, we show that the problem is fixed-parameter tractable on graphs of order $n$ and minimum degree at least $βn$ for some $β> \frac{1}{2}$, where $β$ is the parameter.

cs.DS↗