@misc{ShinanoAchterbergBertholdetal., author = {Shinano, Yuji and Achterberg, Tobias and Berthold, Timo and Heinz, Stefan and Koch, Thorsten and Winkler, Michael}, title = {Solving Open MIP Instances with ParaSCIP on Supercomputers using up to 80,000 Cores}, issn = {1438-0064}, doi = {10.1109/IPDPS.2016.56}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-56404}, abstract = {This paper describes how we solved 12 previously unsolved mixed-integer program- ming (MIP) instances from the MIPLIB benchmark sets. To achieve these results we used an enhanced version of ParaSCIP, setting a new record for the largest scale MIP computation: up to 80,000 cores in parallel on the Titan supercomputer. In this paper we describe the basic parallelization mechanism of ParaSCIP, improvements of the dynamic load balancing and novel techniques to exploit the power of parallelization for MIP solving. We give a detailed overview of computing times and statistics for solving open MIPLIB instances.}, language = {en} } @misc{Shinano, author = {Shinano, Yuji}, title = {UG - Ubiquity Generator Framework v0.9.1}, doi = {10.12752/8508}, abstract = {UG is a generic framework to parallelize branch-and-bound based solvers (e.g., MIP, MINLP, ExactIP) in a distributed or shared memory computing environment. It exploits the powerful performance of state-of-the-art "base solvers", such as SCIP, CPLEX, etc. without the need for base solver parallelization. UG framework, ParaSCIP(ug[SCIP,MPI]) and FiberSCIP (ug[SCIP,Pthreads]) are available as a beta version. For MIP solving, ParaSCIP and FiberSCIP are well debugged and should be stable. For MINLP solving, they are relatively stable, but not as thoroughly debugged. This release version should handle branch-and-cut approaches where subproblems are defined by variable bounds and also by constrains for ug[SCIP,*] ParaSCIP and FiberSCIP). Therefore, problem classes other than MIP or MINLP can be handled, but they have not been tested yet. v0.9.1: Update orbitope cip files.}, 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{Shinano, author = {Shinano, Yuji}, title = {UG - Ubiquity Generator Framework v1.0.0beta}, doi = {10.12752/8521}, abstract = {UG is a generic framework to parallelize branch-and-bound based solvers (e.g., MIP, MINLP, ExactIP) in a distributed or shared memory computing environment. It exploits the powerful performance of state-of-the-art "base solvers", such as SCIP, CPLEX, etc. without the need for base solver parallelization. UG framework, ParaSCIP(ug[SCIP,MPI]) and FiberSCIP (ug[SCIP,Pthreads]) are available as a beta version. v1.0.0: new documentation and cmake, generalization of ug framework, implementation of selfsplitrampup for fiber- and parascip, better memory and time limit handling.}, language = {en} } @misc{Schaefer, author = {Sch{\"a}fer, Patrick}, title = {Bag-Of-SFA-Symbols in Vector Space (BOSS VS)}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-54984}, abstract = {Time series classification mimics the human understanding of similarity. When it comes to larger datasets, state of the art classifiers reach their limits in terms of unreasonable training or testing times. One representative example is the 1-nearest-neighbor DTW classifier (1-NN DTW) that is commonly used as the benchmark to compare to and has several shortcomings: it has a quadratic time and it degenerates in the presence of noise. To reduce the computational complexity lower bounding techniques or recently a nearest centroid classifier have been introduced. Still, execution times to classify moderately sized datasets on a single core are in the order of hours. We present our Bag-Of-SFA-Symbols in Vector Space (BOSS VS) classifier that is robust and accurate due to invariance to noise, phase shifts, offsets, amplitudes and occlusions. We show that it is as accurate while being multiple orders of magnitude faster than state of the art classifiers. Using the BOSS VS allows for mining massive time series datasets and real-time analytics.}, 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{QuerDonatiKelleretal., author = {Quer, Jannes and Donati, Luca and Keller, Bettina and Weber, Marcus}, title = {An automatic adaptive importance sampling algorithm for molecular dynamics in reaction coordinates}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-62075}, abstract = {In this article we propose an adaptive importance sampling scheme for dynamical quantities of high dimensional complex systems which are metastable. The main idea of this article is to combine a method coming from Molecular Dynamics Simulation, Metadynamics, with a theorem from stochastic analysis, Girsanov's theorem. The proposed algorithm has two advantages compared to a standard estimator of dynamic quantities: firstly, it is possible to produce estimators with a lower variance and, secondly, we can speed up the sampling. One of the main problems for building importance sampling schemes for metastable systems is to find the metastable region in order to manipulate the potential accordingly. Our method circumvents this problem by using an assimilated version of the Metadynamics algorithm and thus creates a non-equilibrium dynamics which is used to sample the equilibrium quantities.}, language = {en} } @misc{PfeufferWerner, author = {Pfeuffer, Frank and Werner, Axel}, title = {Adaptive telecommunication network operation with a limited number of reconfigurations}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-55547}, abstract = {Rising traffic in telecommunication networks lead to rising energy costs for the network operators. Meanwhile, increased flexibility of the networking hardware may help to realize load-adaptive operation of the networks to cut operation costs. To meet network operators' concerns over stability, we propose to switch network configurations only a limited number of times per day. We present a method for the integrated computation of optimal switching times and network configurations that alternatingly solves mixed-integer programs and constrained shortest cycle problems in a certain graph. Similarly to the Branch \& Bound Algorithm, it uses lower and upper bounds on the optimum value and allows for pivoting strategies to guide the computation and avoid the solution of irrelevant subproblems. The algorithm can act as a framework to be adapted and applied to suitable problems of different origin.}, language = {en} } @misc{Paskin, type = {Master Thesis}, author = {Paskin, Martha}, title = {Estimating 3D Shape of the Head Skeleton of Basking Sharks Using Annotated Landmarks on a 2D Image}, abstract = {Basking sharks are thought to be one of the most efficient filter-feeding fish in terms of the throughput of water filtered through their gills. Details about the underlying morphology of their branchial region have not been studied due to various challenges in acquiring real-world data. The present thesis aims to facilitate this, by developing a mathematical shape model which constructs the 3D structure of the head skeleton of a basking shark using annotated landmarks on a single 2D image. This is an ill-posed problem as estimating the depth of a 3D object from a single 2D view is, in general, not possible. To reduce this ambiguity, we create a set of pre-defined training shapes in 3D from CT scans of basking sharks. First, the damaged structures of the sharks in the scans are corrected via solving a set of optimization problems, before using them as accurate 3D representations of the object. Then, two approaches are employed for the 2D-to-3D shape fitting problem-an Active Shape Model approach and a Kendall's Shape Space approach. The former represents a shape as a point on a high-dimensional Euclidean space, whereas the latter represents a shape as an equivalence class of points in this Euclidean space. Kendall's shape space approach is a novel technique that has not yet been applied in this context, and a comprehensive comparison of the two approaches suggests this approach to be superior for the problem at hand. This can be credited to an improved interpolation of the training shapes.}, language = {en} } @misc{OrlowskiWernerWessaely, author = {Orlowski, Sebastian and Werner, Axel and Wess{\"a}ly, Roland}, title = {Estimating trenching costs in FTTx network planning}, issn = {1438-0064}, doi = {10.1007/978-3-642-29210-1_15}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-14884}, abstract = {In this paper we assess to which extent trenching costs of an FTTx network are unavoidable, even if technical side constraints are neglected. For that purpose we present an extended Steiner tree model. Using a variety of realistic problem instances we demonstrate that the total trenching cost can only be reduced by about 5 percent in realistic scenarios. This work has been funded by BMBF (German Federal Ministry of Education and Research) within the program "KMU-innovativ".}, language = {en} } @misc{NielsenWeber, author = {Nielsen, Adam and Weber, Marcus}, title = {Computing the nearest reversible Markov chain}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-53292}, abstract = {Reversible Markov chains are the basis of many applications. However, computing transition probabilities by a finite sampling of a Markov chain can lead to truncation errors. Even if the original Markov chain is reversible, the approximated Markov chain might be non-reversible and will lose important properties, like the real valued spectrum. In this paper, we show how to find the closest reversible Markov chain to a given transition matrix. It turns out that this matrix can be computed by solving a convex minimization problem.}, 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{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{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{LieSullivanTeckentrup, author = {Lie, Han Cheng and Sullivan, T. J. and Teckentrup, Aretha}, title = {Random forward models and log-likelihoods in Bayesian inverse problems}, series = {SIAM/ASA Journal on Uncertainty Quantification}, volume = {6}, journal = {SIAM/ASA Journal on Uncertainty Quantification}, number = {4}, issn = {1438-0064}, doi = {10.1137/18M1166523}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-66324}, pages = {1600 -- 1629}, abstract = {We consider the use of randomised forward models and log-likelihoods within the Bayesian approach to inverse problems. Such random approximations to the exact forward model or log-likelihood arise naturally when a computationally expensive model is approximated using a cheaper stochastic surrogate, as in Gaussian process emulation (kriging), or in the field of probabilistic numerical methods. We show that the Hellinger distance between the exact and approximate Bayesian posteriors is bounded by moments of the difference between the true and approximate log-likelihoods. Example applications of these stability results are given for randomised misfit models in large data applications and the probabilistic solution of ordinary differential equations.}, language = {en} } @misc{Keidel, type = {Master Thesis}, author = {Keidel, Stefan}, title = {Snapshots in Scalaris}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42282}, school = {Zuse Institute Berlin (ZIB)}, pages = {87}, abstract = {Eines der gr{\"o}ßten Hindernisse beim praktischen Einsatz von Scalaris, einer skalierbaren Implementierung einer verteilten Hashtabelle mit Unterst{\"u}tzung f{\"u}r Transaktionen, ist das Fehlen eines Verfahrens zur Aufnahme eines konsistenten Zustandes des gesamten Systems. Wir stellen in dieser Arbeit ein einfaches Protokoll vor, dass diese Aufgabe erf{\"u}llt und sich, auf Grund der von uns gew{\"a}hlten Herangehensweise, leicht implementieren l{\"a}sst. Als Ausgangspunkt daf{\"u}r w{\"a}hlen wir aus einer Reihe von „klassischen" Snapshot-Algorithmen ein 1993 von Mattern entworfenes Verfahren, welches auf dem Algorithmus von Lai und Yang basiert, aus. Diese Entscheidung basiert auf einer gr{\"u}ndlichen Analyse der Protokolle unter Ber{\"u}cksichtigung der Architektur der existierenden Software. Im n{\"a}chsten Arbeitsschritt benutzen wir unser vollst{\"a}ndiges Wissen {\"u}ber die Interna des Transaktionssystems von Scalaris und vereinfachen damit das Verfahren hinsichtlich Benutzbarkeit und Implementierungskomplexit{\"a}t, ohne die Anforderungen an den aufgenommenen Zustand aufzuweichen. Statt einer losen Anh{\"a}ufung lokaler Zust{\"a}nde der einzelnen Teilnehmerknoten k{\"o}nnen wir am Ende eine große Schl{\"u}ssel-Wert-Tabelle als Ergebnis erzeugen, die konsistent ist, sich leicht weiterverarbeiten l{\"a}sst und die einem Zustand entspricht, in dem sich das System einmal befunden haben k{\"o}nnte. Nachdem wir das Verfahren dann in Software umgesetzt haben, werten wir die Ergebnisse hinsichtlich des Einflusses auf die Performanz des Gesamtsystems aus und diskutieren m{\"o}gliche Weiterentwicklungen.}, language = {de} } @misc{KaplanLauferProhaskaetal., author = {Kaplan, Bernhard and Laufer, Jan and Prohaska, Steffen and Buchmann, Jens}, title = {Monte-Carlo-based inversion scheme for 3D quantitative photoacoustic tomography}, issn = {1438-0064}, doi = {10.1117/12.2251945}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-62318}, abstract = {The goal of quantitative photoacoustic tomography (qPAT) is to recover maps of the chromophore distributions from multiwavelength images of the initial pressure. Model-based inversions that incorporate the physical processes underlying the photoacoustic (PA) signal generation represent a promising approach. Monte-Carlo models of the light transport are computationally expensive, but provide accurate fluence distributions predictions, especially in the ballistic and quasi-ballistic regimes. Here, we focus on the inverse problem of 3D qPAT of blood oxygenation and investigate the application of the Monte-Carlo method in a model-based inversion scheme. A forward model of the light transport based on the MCX simulator and acoustic propagation modeled by the k-Wave toolbox was used to generate a PA image data set acquired in a tissue phantom over a planar detection geometry. The combination of the optical and acoustic models is shown to account for limited-view artifacts. In addition, the errors in the fluence due to, for example, partial volume artifacts and absorbers immediately adjacent to the region of interest are investigated. To accomplish large-scale inversions in 3D, the number of degrees of freedom is reduced by applying image segmentation to the initial pressure distribution to extract a limited number of regions with homogeneous optical parameters. The absorber concentration in the tissue phantom was estimated using a coordinate descent parameter search based on the comparison between measured and modeled PA spectra. The estimated relative concentrations using this approach lie within 5 \% compared to the known concentrations. Finally, we discuss the feasibility of this approach to recover the blood oxygenation from experimental data.}, language = {en} } @misc{Hoffmann, type = {Master Thesis}, author = {Hoffmann, Marie}, title = {Approximate Algorithms for Distributed Systems}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-42370}, school = {Zuse Institute Berlin (ZIB)}, pages = {75}, abstract = {Peer-to-peer (P2P) systems form a special class of distributed systems. Typically, nodes in a P2P system are flat and share the same responsabilities. In this thesis we focus on three problems that occur in P2P systems: the storage of data replicates, quantile computation on distributed data streams, and churn rate estimation. Data replication is one of the oldest techniques to maintain stored data in a P2P system and to reply to read requests. Applications, which use data replication are distributed databases. They are part of an abstract overlay network and do not see the underlying network topology. The question is how to place a set of data replicates in a distributed system such that response times and failure probabilities become minimal without a priori knowledge of the topology of the underlying hardware nodes? We show how to utilize an agglomerative clustering procedure to reach this goal. State-of-the-art algorithms for aggregation of distributed data or data streams require at some point synchronization, or merge data aggregates hierarchically, which does not accompany the basic principle of P2P systems. We test whether randomized communication and merging of data aggregates are able to produce the same results. These data aggregates serve for quantile queries. Constituting and maintaining a P2P overlay network requires frequent message passing. It is a goal to minimize the number of maintenance messages since they consume bandwidth which might be missing for other applications. The lower bound of the frequency for mainte- nance messages is highly dependent on the churn rate of peers. We show how to estimate the mean lifetime of peers and to reduce the frequency for maintenance messages without destabilizing the infrastructure of the constituting overlay.}, language = {en} } @misc{HillerVredeveld, author = {Hiller, Benjamin and Vredeveld, Tjark}, title = {Stochastic dominance analysis of Online Bin Coloring algorithms}, issn = {1438-0064}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-16502}, abstract = {This paper proposes a new method for probabilistic analysis of online algorithms. It is based on the notion of stochastic dominance. We develop the method for the online bin coloring problem introduced by Krumke et al (2008). Using methods for the stochastic comparison of Markov chains we establish the result that the performance of the online algorithm GreedyFit is stochastically better than the performance of the algorithm OneBin for any number of items processed. This result gives a more realistic picture than competitive analysis and explains the behavior observed in simulations.}, language = {en} } @misc{HillerVredeveld, author = {Hiller, Benjamin and Vredeveld, Tjark}, title = {Probabilistic alternatives for competitive analysis}, issn = {1438-0064}, doi = {10.1007/s00450-011-0149-1}, url = {http://nbn-resolving.de/urn:nbn:de:0297-zib-15131}, abstract = {In the last 20 years competitive analysis has become the main tool for analyzing the quality of online algorithms. Despite of this, competitive analysis has also been criticized: It sometimes cannot discriminate between algorithms that exhibit significantly different empirical behavior, or it even favors an algorithm that is worse from an empirical point of view. Therefore, there have been several approaches to circumvent these drawbacks. In this survey, we discuss probabilistic alternatives for competitive analysis.}, language = {en} }