@misc{VuLitzelKoch2025, author = {Vu, Thi Huong and Litzel, Ida and Koch, Thorsten}, title = {Similarity-based fuzzy clustering scientific articles: potentials and challenges from mathematical and computational perspectives}, arxiv = {http://arxiv.org/abs/2506.04045}, year = {2025}, abstract = {Fuzzy clustering, which allows an article to belong to multiple clusters with soft membership degrees, plays a vital role in analyzing publication data. This problem can be formulated as a constrained optimization model, where the goal is to minimize the discrepancy between the similarity observed from data and the similarity derived from a predicted distribution. While this approach benefits from leveraging state-of-the-art optimization algorithms, tailoring them to work with real, massive databases like OpenAlex or Web of Science -- containing about 70 million articles and a billion citations -- poses significant challenges. We analyze potentials and challenges of the approach from both mathematical and computational perspectives. Among other things, second-order optimality conditions are established, providing new theoretical insights, and practical solution methods are proposed by exploiting the problem's structure. Specifically, we accelerate the gradient projection method using GPU-based parallel computing to efficiently handle large-scale data.}, language = {en} } @misc{ShinanoAchterbergBertholdetal.2010, author = {Shinano, Yuji and Achterberg, Tobias and Berthold, Timo and Heinz, Stefan and Koch, Thorsten}, title = {ParaSCIP - a parallel extension of SCIP}, doi = {10.1007/978-3-642-24025-6_12}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-11921}, number = {10-27}, year = {2010}, abstract = {Mixed integer programming (MIP) has become one of the most important techniques in Operations Research and Discrete Optimization. SCIP (Solving Constraint Integer Programs) is currently one of the fastest non-commercial MIP solvers. It is based on the branch-and-bound procedure in which the problem is recursively split into smaller subproblems, thereby creating a so-called branching tree. We present ParaSCIP, an extension of SCIP, which realizes a parallelization on a distributed memory computing environment. ParaSCIP uses SCIP solvers as independently running processes to solve subproblems (nodes of the branching tree) locally. This makes the parallelization development independent of the SCIP development. Thus, ParaSCIP directly profits from any algorithmic progress in future versions of SCIP. Using a first implementation of ParaSCIP, we were able to solve two previously unsolved instances from MIPLIB2003, a standard test set library for MIP solvers. For these computations, we used up to 2048 cores of the HLRN~II supercomputer.}, language = {en} } @misc{ShinanoAchterbergBertholdetal.2013, author = {Shinano, Yuji and Achterberg, Tobias and Berthold, Timo and Heinz, Stefan and Koch, Thorsten and Vigerske, Stefan and Winkler, Michael}, title = {制約整数計画ソルバ SCIP の並列化}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-18130}, year = {2013}, abstract = {制約整数計画(CIP: Constraint Integer Programming)は,制約プログラミング(CP: Constraint Programming),混合整数計画(MIP: Mixed Integer Programming), 充足可能性問題(SAT: Satisfiability Problems)の研究分野におけるモデリング技術と解法を統合している.その結果,制約整数計画は,広いクラスの最適化問題を扱うことができる.SCIP (Solving Constraint Integer Programs)は,CIPを解くソルバとして実装され,Zuse Institute Berlin (ZIB)の研究者を中心として継続的に拡張が続けられている.本論文では,著者らによって開発されたSCIP に対する2種類の並列化拡張を紹介する. 一つは,複数計算ノード間で大規模に並列動作するParaSCIP である. もう一つは,複数コアと共有メモリを持つ1台の計算機上で(スレッド)並列で動作するFiberSCIP である. ParaSCIP は,HLRN IIスーパーコンピュータ上で, 一つのインスタンスを解くために最大7,168 コアを利用した動作実績がある.また,統計数理研究所のFujitsu PRIMERGY RX200S5上でも,最大512コアを利用した動作実績がある.統計数理研究所のFujitsu PRIMERGY RX200S5上 では,これまでに最適解が得られていなかったMIPLIB2010のインスタンスであるdg012142に最適解を与えた.}, language = {ja} }