arXiv subjects
Publications and source records attributed to Amir Nayyeri.
We present a linear time algorithm for computing a cycle separator in a planar graph that is (arguably) simpler than previously known algorithms. Our algorithm builds on, and is somewhat similar to, previous algorithms for computing separators. The main new ingredient is a specific layered decomposition of the planar graph constructed differently from previous BFS-based layerings.
It is known that annotating named entities in unstructured and semi-structured data sets by their concepts improves the effectiveness of answering queries over these data sets. As every enterprise has a limited budget of time or computational resources, it has to annotate a subset of concepts in a given domain whose costs of annotation do not exceed the budget. We call such a subset of concepts a {\it conceptual design} for the annotated data set. We focus on finding a conceptual design that provides the most effective answers to queries over the annotated data set, i.e., a {\it cost-effective conceptual design}. Since, it is often less time-consuming and costly to annotate general concepts than specific concepts, we use information on superclass/subclass relationships between concepts in taxonomies to find a cost-effective conceptual design. We quantify the amount by which a conceptual design with concepts from a taxonomy improves the effectiveness of answering queries over an annotated data set. If the taxonomy is a tree, we prove that the problem is NP-hard and propose an efficient approximation and pseudo-polynomial time algorithms for the problem. We further prove that if the taxonomy is a directed acyclic graph, given some generally accepted hypothesis, it is not possible to find any approximation algorithm with reasonably small approximation ratio for the problem. Our empirical study using real-world data sets, taxonomies, and query workloads shows that our framework effectively quantifies the amount by which a conceptual design improves the effectiveness of answering queries. It also indicates that our algorithms are efficient for a design-time task with pseudo-polynomial algorithm being generally more effective than the approximation algorithm.
We study the problems of finding a minimum cycle basis (a minimum weight set of cycles that form a basis for the cycle space) and a minimum homology basis (a minimum weight set of cycles that generates the $1$-dimensional ($\mathbb{Z}_2$)-homology classes) of an undirected graph embedded on a surface. The problems are closely related, because the minimum cycle basis of a graph contains its minimum homology basis, and the minimum homology basis of the $1$-skeleton of any graph is exactly its minimum cycle basis. For the minimum cycle basis problem, we give a deterministic $O(n^ω+2^{2g}n^2+m)$-time algorithm for graphs embedded on an orientable surface of genus $g$. The best known existing algorithms for surface embedded graphs are those for general graphs: an $O(m^ω)$ time Monte Carlo algorithm and a deterministic $O(nm^2/\log n + n^2 m)$ time algorithm. For the minimum homology basis problem, we give a deterministic $O((g+b)^3 n \log n + m)$-time algorithm for graphs embedded on an orientable or non-orientable surface of genus $g$ with $b$ boundary components, assuming shortest paths are unique, improving on existing algorithms for many values of $g$ and $n$. The assumption of unique shortest paths can be avoided with high probability using randomization or deterministically by increasing the running time of the homology basis algorithm by a factor of $O(\log n)$.
For an undirected $n$-vertex graph $G$ with non-negative edge-weights, we consider the following type of query: given two vertices $s$ and $t$ in $G$, what is the weight of a minimum $st$-cut in $G$? We solve this problem in preprocessing time $O(n\log^3 n)$ for graphs of bounded genus, giving the first sub-quadratic time algorithm for this class of graphs. Our result also improves by a logarithmic factor a previous algorithm by Borradaile, Sankowski and Wulff-Nilsen (FOCS 2010) that applied only to planar graphs. Our algorithm constructs a Gomory-Hu tree for the given graph, providing a data structure with space $O(n)$ that can answer minimum-cut queries in constant time. The dependence on the genus of the input graph in our preprocessing time is $2^{O(g^2)}$.
We describe a $O(\log n )$-approximation algorithm for computing the homotopic \Frechet distance between two polygonal curves that lie on the boundary of a triangulated topological disk. Prior to this work, algorithms were known only for curves on the Euclidean plane with polygonal obstacles. A key technical ingredient in our analysis is a $O(\log n)$-approximation algorithm for computing the minimum height of a homotopy between two curves. No algorithms were previously known for approximating this parameter. Surprisingly, it is not even known if computing either the homotopic \Frechet distance, or the minimum height of a homotopy, is in NP.
Given $k$ pairs of terminals $\{(s_{1}, t_{1}), \ldots, (s_{k}, t_{k})\}$ in a graph $G$, the min-sum $k$ vertex-disjoint paths problem is to find a collection $\{Q_{1}, Q_{2}, \ldots, Q_{k}\}$ of vertex-disjoint paths with minimum total length, where $Q_{i}$ is an $s_i$-to-$t_i$ path between $s_i$ and $t_i$. We consider the problem in planar graphs, where little is known about computational tractability, even in restricted cases. Kobayashi and Sommer propose a polynomial-time algorithm for $k \le 3$ in undirected planar graphs assuming all terminals are adjacent to at most two faces. Colin de Verdiere and Schrijver give a polynomial-time algorithm when all the sources are on the boundary of one face and all the sinks are on the boundary of another face and ask about the existence of a polynomial-time algorithm provided all terminals are on a common face. We make progress toward Colin de Verdiere and Schrijver's open question by giving an $O(kn^5)$ time algorithm for undirected planar graphs when $\{(s_{1}, t_{1}), \ldots, (s_{k}, t_{k})\}$ are in counter-clockwise order on a common face.
Several researchers proposed using non-Euclidean metrics on point sets in Euclidean space for clustering noisy data. Almost always, a distance function is desired that recognizes the closeness of the points in the same cluster, even if the Euclidean cluster diameter is large. Therefore, it is preferred to assign smaller costs to the paths that stay close to the input points. In this paper, we consider the most natural metric with this property, which we call the nearest neighbor metric. Given a point set P and a path $γ$, our metric charges each point of $γ$ with its distance to P. The total charge along $γ$ determines its nearest neighbor length, which is formally defined as the integral of the distance to the input points along the curve. We describe a $(3+\varepsilon)$-approximation algorithm and a $(1+\varepsilon)$-approximation algorithm to compute the nearest neighbor metric. Both approximation algorithms work in near-linear time. The former uses shortest paths on a sparse graph using only the input points. The latter uses a sparse sample of the ambient space, to find good approximate geodesic paths.