@misc{DercksenHegeOberlaender2013, author = {Dercksen, Vincent J. and Hege, Hans-Christian and Oberlaender, Marcel}, title = {The Filament Editor: An Interactive Software Environment for Visualization, Proof-Editing and Analysis of 3D Neuron Morphology}, issn = {1438-0064}, doi = {10.1007/s12021-013-9213-2}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-43157}, year = {2013}, abstract = {Neuroanatomical analysis, such as classification of cell types, depends on reliable reconstruction of large numbers of complete 3D dendrite and axon morphologies. At present, the majority of neuron reconstructions are obtained from preparations in a single tissue slice in vitro, thus suffering from cut off dendrites and, more dramatically, cut off axons. In general, axons can innervate volumes of several cubic millimeters and may reach path lengths of tens of centimeters. Thus, their complete reconstruction requires in vivo labeling, histological sectioning and imaging of large fields of view. Unfortunately, anisotropic background conditions across such large tissue volumes, as well as faintly labeled thin neurites, result in incomplete or erroneous automated tracings and even lead experts to make annotation errors during manual reconstructions. Consequently, tracing reliability renders the major bottleneck for reconstructing complete 3D neuron morphologies. Here, we present a novel set of tools, integrated into a software environment named 'Filament Editor', for creating reliable neuron tracings from sparsely labeled in vivo datasets. The Filament Editor allows for simultaneous visualization of complex neuronal tracings and image data in a 3D viewer, proof-editing of neuronal tracings, alignment and interconnection across sections, and morphometric analysis in relation to 3D anatomical reference structures. We illustrate the functionality of the Filament Editor on the example of in vivo labeled axons and demonstrate that for the exemplary dataset the final tracing results after proof-editing are independent of the expertise of the human operator.}, language = {en} } @misc{Shinano, author = {Shinano, Yuji}, title = {The Ubiquity Generator Framework: 7 Years of Progress in Parallelizing Branch-and-Bound}, issn = {1438-0064}, doi = {10.1007/978-3-319-89920-6_20}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-65545}, abstract = {Mixed integer linear programming (MIP) is a general form to model combinatorial optimization problems and has many industrial applications. The performance of MIP solvers has improved tremendously in the last two decades and these solvers have been used to solve many real-word problems. However, against the backdrop of modern computer technology, parallelization is of pivotal importance. In this way, ParaSCIP is the most successful parallel MIP solver in terms of solving previously unsolvable instances from the well-known benchmark instance set MIPLIB by using supercomputers. It solved two instances from MIPLIB2003 and 12 from MIPLIB2010 for the first time to optimality by using up to 80,000 cores on supercomputers. ParaSCIP has been developed by using the Ubiquity Generator (UG) framework, which is a general software package to parallelize any state-of-the-art branch-and-bound based solver. This paper discusses 7 years of progress in parallelizing branch-and-bound solvers with UG.}, language = {en} } @misc{FujiiItoKimetal., author = {Fujii, Koichi and Ito, Naoki and Kim, Sunyoung and Kojima, Masakazu and Shinano, Yuji and Toh, Kim-Chuan}, title = {大規模二次割当問題への挑戦}, series = {統計数理研究所共同研究リポート 453 最適化:モデリングとアルゴリズム33 2022年3月 「大規模二次割当問題への挑戦」 p.84-p.92}, journal = {統計数理研究所共同研究リポート 453 最適化:モデリングとアルゴリズム33 2022年3月 「大規模二次割当問題への挑戦」 p.84-p.92}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-86779}, abstract = {二次割当問題は線形緩和が弱いことが知られ,強化のため多様な緩和手法が考案されているが,その一つである二重非負値計画緩和( DNN 緩和)及びその解法として近年研究が進んでいるニュートン・ブラケット法を紹介し,それらに基づく分枝限定法の実装及び数値実験結果について報告する.}, language = {ja} } @misc{WeberTranfieldHoeoegetal., author = {Weber, Britta and Tranfield, Erin M. and H{\"o}{\"o}g, Johanna L. and Baum, Daniel and Antony, Claude and Hyman, Tony and Verbavatz, Jean-Marc and Prohaska, Steffen}, title = {Automated stitching of microtubule centerlines across serial electron tomograms}, issn = {1438-0064}, doi = {10.1371/journal.pone.0113222}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-52958}, abstract = {Tracing microtubule centerlines in serial section electron tomography requires microtubules to be stitched across sections, that is lines from different sections need to be aligned, endpoints need to be matched at section boundaries to establish a correspondence between neighboring sections, and corresponding lines need to be connected across multiple sections. We present computational methods for these tasks: 1) An initial alignment is computed using a distance compatibility graph. 2) A fine alignment is then computed with a probabilistic variant of the iterative closest points algorithm, which we extended to handle the orientation of lines by introducing a periodic random variable to the probabilistic formulation. 3) Endpoint correspondence is established by formulating a matching problem in terms of a Markov random field and computing the best matching with belief propagation. Belief propagation is not generally guaranteed to converge to a minimum. We show how convergence can be achieved, nonetheless, with minimal manual input. In addition to stitching microtubule centerlines, the correspondence is also applied to transform and merge the electron tomograms. We applied the proposed methods to samples from the mitotic spindle in C. elegans, the meiotic spindle in X. laevis, and sub-pellicular microtubule arrays in T. brucei. The methods were able to stitch microtubules across section boundaries in good agreement with experts' opinions for the spindle samples. Results, however, were not satisfactory for the microtubule arrays. For certain experiments, such as an analysis of the spindle, the proposed methods can replace manual expert tracing and thus enable the analysis of microtubules over long distances with reasonable manual effort.}, language = {en} } @misc{ShinanoRehfeldtKoch, author = {Shinano, Yuji and Rehfeldt, Daniel and Koch, Thorsten}, title = {Building Optimal Steiner Trees on Supercomputers by using up to 43,000 Cores}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-71118}, abstract = {SCIP-JACK is a customized, branch-and-cut based solver for Steiner tree and related problems. ug [SCIP-JACK, MPI] extends SCIP-JACK to a massively par- allel solver by using the Ubiquity Generator (UG) framework. ug [SCIP-JACK, MPI] was the only solver that could run on a distributed environment at the (latest) 11th DIMACS Challenge in 2014. Furthermore, it could solve three well-known open instances and updated 14 best known solutions to instances from the bench- mark libary STEINLIB. After the DIMACS Challenge, SCIP-JACK has been con- siderably improved. However, the improvements were not reflected on ug [SCIP- JACK, MPI]. This paper describes an updated version of ug [SCIP-JACK, MPI], especially branching on constrains and a customized racing ramp-up. Furthermore, the different stages of the solution process on a supercomputer are described in detail. We also show the latest results on open instances from the STEINLIB.}, language = {en} } @misc{WendeSteinke, author = {Wende, Florian and Steinke, Thomas}, title = {Swendsen-Wang Multi-Cluster Algorithm for the 2D/3D Ising Model on Xeon Phi and GPU}, issn = {1438-0064}, doi = {10.1145/2503210.2503254}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42187}, abstract = {Simulations of the critical Ising model by means of local update algorithms suffer from critical slowing down. One way to partially compensate for the influence of this phenomenon on the runtime of simulations is using increasingly faster and parallel computer hardware. Another approach is using algorithms that do not suffer from critical slowing down, such as cluster algorithms. This paper reports on the Swendsen-Wang multi-cluster algorithm on Intel Xeon Phi coprocessor 5110P, Nvidia Tesla M2090 GPU, and x86 multi-core CPU. We present shared memory versions of the said algorithm for the simulation of the two- and three-dimensional Ising model. We use a combination of local cluster search and global label reduction by means of atomic hardware primitives. Further, we describe an MPI version of the algorithm on Xeon Phi and CPU, respectively. Significant performance improvements over known im plementations of the Swendsen-Wang algorithm are demonstrated.}, language = {en} } @misc{HosodaMaherShinanoetal., author = {Hosoda, Junko and Maher, Stephen J. and Shinano, Yuji and Villumsen, Jonas Christoffer}, title = {A parallel branch-and-bound heuristic for the integrated long-haul and local vehicle routing problem on an adaptive transportation network}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-89700}, abstract = {Consolidation of commodities and coordination of vehicle routes are fundamental features of supply chain management problems. While locations for consolidation and coordination are typically known a priori, in adaptive transportation networks this is not the case. The identification of such consolidation locations forms part of the decision making process. Supply chain management problems integrating the designation of consolidation locations with the coordination of long haul and local vehicle routing is not only challenging to solve, but also very difficult to formulate mathematically. In this paper, the first mathematical model integrating location clustering with long haul and local vehicle routing is proposed. This mathematical formulation is used to develop algorithms to find high quality solutions. A novel parallel framework is developed that combines exact and heuristic methods to improve the search for high quality solutions and provide valid bounds. The results demonstrate that using exact methods to guide heuristic search is an effective approach to find high quality solutions for difficult supply chain management problems.}, language = {en} } @misc{MunguiaOxberryRajanetal., author = {Munguia, Lluis-Miquel and Oxberry, Geoffrey and Rajan, Deepak and Shinano, Yuji}, title = {Parallel PIPS-SBB: Multi-Level Parallelism For Stochastic Mixed-Integer Programs}, number = {ZIB-Report 17-58}, issn = {1438-0064}, doi = {10.1007/s10589-019-00074-0}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-65517}, abstract = {PIPS-SBB is a distributed-memory parallel solver with a scalable data distribution paradigm. It is designed to solve MIPs with a dual-block angular structure, which is characteristic of deterministic-equivalent Stochastic Mixed-Integer Programs (SMIPs). In this paper, we present two different parallelizations of Branch \& Bound (B\&B), implementing both as extensions of PIPS-SBB, thus adding an additional layer of parallelism. In the first of the proposed frameworks, PIPS-PSBB, the coordination and load-balancing of the different optimization workers is done in a decentralized fashion. This new framework is designed to ensure all available cores are processing the most promising parts of the B\&B tree. The second, ug[PIPS-SBB,MPI], is a parallel implementation using the Ubiquity Generator (UG), a universal framework for parallelizing B\&B tree search that has been successfully applied to other MIP solvers. We show the effects of leveraging multiple levels of parallelism in potentially improving scaling performance beyond thousands of cores.}, language = {en} } @misc{GriewankStreubelLehmannetal., author = {Griewank, Andreas and Streubel, Tom and Lehmann, Lutz and Hasenfelder, Richard and Radons, Manuel}, title = {Piecewise linear secant approximation via Algorithmic Piecewise Differentiation}, issn = {1438-0064}, doi = {10.1080/10556788.2017.1387256}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-61642}, abstract = {It is shown how piecewise differentiable functions \(F: R^n → R^m\) that are defined by evaluation programs can be approximated locally by a piecewise linear model based on a pair of sample points x̌ and x̂. We show that the discrepancy between function and model at any point x is of the bilinear order O(||x - x̌|| ||x - x̂||). This is a little surprising since x ∈ R^n may vary over the whole Euclidean space, and we utilize only two function samples F̌ = F(x̌) and F̂ = F(x̂), as well as the intermediates computed during their evaluation. As an application of the piecewise linearization procedure we devise a generalized Newton's method based on successive piecewise linearization and prove for it sufficient conditions for convergence and convergence rates equaling those of semismooth Newton. We conclude with the derivation of formulas for the numerically stable implementation of the aforedeveloped piecewise linearization methods.}, language = {en} } @misc{LindnerReisch, author = {Lindner, Niels and Reisch, Julian}, title = {Parameterized Complexity of Periodic Timetabling}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-78314}, abstract = {Public transportation networks are typically operated with a periodic timetable. The Periodic Event Scheduling Problem (PESP) is the standard mathematical modelling tool for periodic timetabling. Since PESP can be solved in linear time on trees, it is a natural question to ask whether there are polynomial-time algorithms for input networks of bounded treewidth. We show that deciding the feasibility of a PESP instance is NP-hard even when the treewidth is 2, the branchwidth is 2, or the carvingwidth is 3. Analogous results hold for the optimization of reduced PESP instances, where the feasibility problem is trivial. To complete the picture, we present two pseudo-polynomial-time dynamic programming algorithms solving PESP on input networks with bounded tree- or branchwidth. We further analyze the parameterized complexity of PESP with bounded cyclomatic number, diameter, or vertex cover number. For event-activity networks with a special -- but standard -- structure, we give explicit and sharp bounds on the branchwidth in terms of the maximum degree and the carvingwidth of an underlying line network. Finally, we investigate several parameters on the smallest instance of the benchmarking library PESPlib.}, language = {en} } @misc{OezelKulkarniHasanetal., author = {{\"O}zel, M. Neset and Kulkarni, Abhishek and Hasan, Amr and Brummer, Josephine and Moldenhauer, Marian and Daumann, Ilsa-Maria and Wolfenberg, Heike and Dercksen, Vincent J. and Kiral, F. Ridvan and Weiser, Martin and Prohaska, Steffen and von Kleist, Max and Hiesinger, Peter Robin}, title = {Serial synapse formation through filopodial competition for synaptic seeding factors}, issn = {1438-0064}, doi = {10.1016/j.devcel.2019.06.014}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-74397}, abstract = {Following axon pathfinding, growth cones transition from stochastic filopodial exploration to the formation of a limited number of synapses. How the interplay of filopodia and synapse assembly ensures robust connectivity in the brain has remained a challenging problem. Here, we developed a new 4D analysis method for filopodial dynamics and a data-driven computational model of synapse formation for R7 photoreceptor axons in developing Drosophila brains. Our live data support a 'serial synapse formation' model, where at any time point only a single 'synaptogenic' filopodium suppresses the synaptic competence of other filopodia through competition for synaptic seeding factors. Loss of the synaptic seeding factors Syd-1 and Liprin-α leads to a loss of this suppression, filopodial destabilization and reduced synapse formation, which is sufficient to cause the destabilization of entire axon terminals. Our model provides a filopodial 'winner-takes-all' mechanism that ensures the formation of an appropriate number of synapses.}, language = {en} } @misc{MasingLindnerEbert, author = {Masing, Berenike and Lindner, Niels and Ebert, Patricia}, title = {Forward and Line-Based Cycle Bases for Periodic Timetabling}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-89731}, abstract = {The optimization of periodic timetables is an indispensable planning task in public transport. Although the periodic event scheduling problem (PESP) provides an elegant mathematical formulation of the periodic timetabling problem that led to many insights for primal heuristics, it is notoriously hard to solve to optimality. One reason is that for the standard mixed-integer linear programming formulations, linear programming relaxations are weak and the integer variables are of pure technical nature and in general do not correlate with the objective value. While the first problem has been addressed by developing several families of cutting planes, we focus on the second aspect. We discuss integral forward cycle bases as a concept to compute improved dual bounds for PESP instances. To this end, we develop the theory of forward cycle bases on general digraphs. Specifically for the application of timetabling, we devise a generic procedure to construct line-based event-activity networks, and give a simple recipe for an integral forward cycle basis on such networks. Finally, we analyze the 16 railway instances of the benchmark library PESPlib, match them to the line-based structure and use forward cycle bases to compute better dual bounds for 14 out of the 16 instances.}, language = {en} } @misc{RiberaBorrellQuerRichteretal., author = {Ribera Borrell, Enric and Quer, Jannes and Richter, Lorenz and Sch{\"u}tte, Christof}, title = {Improving control based importance sampling strategies for metastable diffusions via adapted metadynamics}, issn = {1438-0064}, abstract = {Sampling rare events in metastable dynamical systems is often a computationally expensive task and one needs to resort to enhanced sampling methods such as importance sampling. Since we can formulate the problem of finding optimal importance sampling controls as a stochastic optimization problem, this then brings additional numerical challenges and the convergence of corresponding algorithms might as well suffer from metastabilty. In this article we address this issue by combining systematic control approaches with the heuristic adaptive metadynamics method. Crucially, we approximate the importance sampling control by a neural network, which makes the algorithm in principle feasible for high dimensional applications. We can numerically demonstrate in relevant metastable problems that our algorithm is more effective than previous attempts and that only the combination of the two approaches leads to a satisfying convergence and therefore to an efficient sampling in certain metastable settings.}, language = {en} } @misc{TateiwaShinanoYasudaetal., author = {Tateiwa, Nariaki and Shinano, Yuji and Yasuda, Masaya and Kaji, Shizuo and Yamamura, Keiichiro and Fujisawa, Katsuki}, title = {Massively parallel sharing lattice basis reduction}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-85209}, abstract = {For cryptanalysis in lattice-based schemes, the performance evaluation of lattice basis reduction using high-performance computers is becoming increasingly important for the determination of the security level. We propose a distributed and asynchronous parallel reduction algorithm based on randomization and DeepBKZ, which is an improved variant of the block Korkine-Zolotarev (BKZ) reduction algorithm. Randomized copies of a lattice basis are distributed to up to 103,680 cores and independently reduced in parallel, while some basis vectors are shared asynchronously among all processes via MPI. There is a trade-off between randomization and information sharing; if a substantial amount of information is shared, all processes will work on the same problem, thereby diminishing the benefit of parallelization. To monitor this balance between randomness and sharing, we propose a metric to quantify the variety of lattice bases. We empirically find an optimal parameter of sharing for high-dimensional lattices. We demonstrate the efficacy of our proposed parallel algorithm and implementation with respect to both performance and scalability through our experiments.}, language = {en} } @misc{TateiwaShinanoYamamuraetal., author = {Tateiwa, Nariaki and Shinano, Yuji and Yamamura, Keiichiro and Yoshida, Akihiro and Kaji, Shizuo and Yasuda, Masaya and Fujisawa, Katsuki}, title = {CMAP-LAP: Configurable Massively Parallel Solver for Lattice Problems}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-82802}, abstract = {Lattice problems are a class of optimization problems that are notably hard. There are no classical or quantum algorithms known to solve these problems efficiently. Their hardness has made lattices a major cryptographic primitive for post-quantum cryptography. Several different approaches have been used for lattice problems with different computational profiles; some suffer from super-exponential time, and others require exponential space. This motivated us to develop a novel lattice problem solver, CMAP-LAP, based on the clever coordination of different algorithms that run massively in parallel. With our flexible framework, heterogeneous modules run asynchronously in parallel on a large-scale distributed system while exchanging information, which drastically boosts the overall performance. We also implement full checkpoint-and-restart functionality, which is vital to high-dimensional lattice problems. Through numerical experiments with up to 103,680 cores, we evaluated the performance and stability of our system and demonstrated its high capability for future massive-scale experiments.}, language = {en} } @misc{FujiiKimKojimaetal., author = {Fujii, Koichi and Kim, Sunyoung and Kojima, Masakazu and Mittelmann, Hans D. and Shinano, Yuji}, title = {An Exceptionally Difficult Binary Quadratic Optimization Problem with Symmetry: a Challenge for The Largest Unsolved QAP Instance Tai256c}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-93072}, abstract = {Tai256c is the largest unsolved quadratic assignment problem (QAP) instance in QAPLIB. It is known that QAP tai256c can be converted into a 256 dimensional binary quadratic optimization problem (BQOP) with a single cardinality constraint which requires the sum of the binary variables to be 92. As the BQOP is much simpler than the original QAP, the conversion increases the possibility to solve the QAP. Solving exactly the BQOP, however, is still very difficult. Indeed, a 1.48\% gap remains between the best known upper bound (UB) and lower bound (LB) of the unknown optimal value. This paper shows that the BQOP admits a nontrivial symmetry, a property that makes the BQOP very hard to solve. The symmetry induces equivalent subproblems in branch and bound (BB) methods. To effectively improve the LB, we propose an efficient BB method that incorporates a doubly nonnegative relaxation, the standard orbit branching and a technique to prune equivalent subproblems. With this BB method, a new LB with 1.25\% gap is successfully obtained, and computing an LB with 1.0\% gap is shown to be still quite difficult.}, language = {en} }