@phdthesis{1399,
abstract = {This thesis is concerned with the computation and approximation of intrinsic volumes. Given a smooth body M and a certain digital approximation of it, we develop algorithms to approximate various intrinsic volumes of M using only measurements taken from its digital approximations. The crucial idea behind our novel algorithms is to link the recent theory of persistent homology to the theory of intrinsic volumes via the Crofton formula from integral geometry and, in particular, via Euler characteristic computations. Our main contributions are a multigrid convergent digital algorithm to compute the first intrinsic volume of a solid body in R^n as well as an appropriate integration pipeline to approximate integral-geometric integrals defined over the Grassmannian manifold.},
author = {Pausinger, Florian},
pages = {144},
publisher = {IST Austria},
title = {{On the approximation of intrinsic volumes}},
year = {2015},
}
@phdthesis{1400,
abstract = {Cancer results from an uncontrolled growth of abnormal cells. Sequentially accumulated genetic and epigenetic alterations decrease cell death and increase cell replication. We used mathematical models to quantify the effect of driver gene mutations. The recently developed targeted therapies can lead to dramatic regressions. However, in solid cancers, clinical responses are often short-lived because resistant cancer cells evolve. We estimated that approximately 50 different mutations can confer resistance to a typical targeted therapeutic agent. We find that resistant cells are likely to be present in expanded subclones before the start of the treatment. The dominant strategy to prevent the evolution of resistance is combination therapy. Our analytical results suggest that in most patients, dual therapy, but not monotherapy, can result in long-term disease control. However, long-term control can only occur if there are no possible mutations in the genome that can cause cross-resistance to both drugs. Furthermore, we showed that simultaneous therapy with two drugs is much more likely to result in long-term disease control than sequential therapy with the same drugs. To improve our understanding of the underlying subclonal evolution we reconstruct the evolutionary history of a patient's cancer from next-generation sequencing data of spatially-distinct DNA samples. Using a quantitative measure of genetic relatedness, we found that pancreatic cancers and their metastases demonstrated a higher level of relatedness than that expected for any two cells randomly taken from a normal tissue. This minimal amount of genetic divergence among advanced lesions indicates that genetic heterogeneity, when quantitatively defined, is not a fundamental feature of the natural history of untreated pancreatic cancers. Our newly developed, phylogenomic tool Treeomics finds evidence for seeding patterns of metastases and can directly be used to discover rules governing the evolution of solid malignancies to transform cancer into a more predictable disease.},
author = {Reiter, Johannes},
pages = {183},
publisher = {IST Austria},
title = {{The subclonal evolution of cancer}},
year = {2015},
}
@inproceedings{1424,
abstract = {We consider the problem of statistical computations with persistence diagrams, a summary representation of topological features in data. These diagrams encode persistent homology, a widely used invariant in topological data analysis. While several avenues towards a statistical treatment of the diagrams have been explored recently, we follow an alternative route that is motivated by the success of methods based on the embedding of probability measures into reproducing kernel Hilbert spaces. In fact, a positive definite kernel on persistence diagrams has recently been proposed, connecting persistent homology to popular kernel-based learning techniques such as support vector machines. However, important properties of that kernel enabling a principled use in the context of probability measure embeddings remain to be explored. Our contribution is to close this gap by proving universality of a variant of the original kernel, and to demonstrate its effective use in twosample hypothesis testing on synthetic as well as real-world data.},
author = {Kwitt, Roland and Huber, Stefan and Niethammer, Marc and Lin, Weili and Bauer, Ulrich},
location = {Montreal, Canada},
pages = {3070 -- 3078},
publisher = {Neural Information Processing Systems},
title = {{Statistical topological data analysis-A kernel perspective}},
volume = {28},
year = {2015},
}
@inproceedings{1425,
abstract = {In this work we aim at extending the theoretical foundations of lifelong learning. Previous work analyzing this scenario is based on the assumption that learning tasks are sampled i.i.d. from a task environment or limited to strongly constrained data distributions. Instead, we study two scenarios when lifelong learning is possible, even though the observed tasks do not form an i.i.d. sample: first, when they are sampled from the same environment, but possibly with dependencies, and second, when the task environment is allowed to change over time in a consistent way. In the first case we prove a PAC-Bayesian theorem that can be seen as a direct generalization of the analogous previous result for the i.i.d. case. For the second scenario we propose to learn an inductive bias in form of a transfer procedure. We present a generalization bound and show on a toy example how it can be used to identify a beneficial transfer algorithm.},
author = {Pentina, Anastasia and Lampert, Christoph},
location = {Montreal, Canada},
pages = {1540 -- 1548},
publisher = {Neural Information Processing Systems},
title = {{Lifelong learning with non-i.i.d. tasks}},
volume = {2015},
year = {2015},
}
@inproceedings{1430,
abstract = {Evolutionary algorithms (EAs) form a popular optimisation paradigm inspired by natural evolution. In recent years the field of evolutionary computation has developed a rigorous analytical theory to analyse their runtime on many illustrative problems. Here we apply this theory to a simple model of natural evolution. In the Strong Selection Weak Mutation (SSWM) evolutionary regime the time between occurrence of new mutations is much longer than the time it takes for a new beneficial mutation to take over the population. In this situation, the population only contains copies of one genotype and evolution can be modelled as a (1+1)-type process where the probability of accepting a new genotype (improvements or worsenings) depends on the change in fitness. We present an initial runtime analysis of SSWM, quantifying its performance for various parameters and investigating differences to the (1+1) EA. We show that SSWM can have a moderate advantage over the (1+1) EA at crossing fitness valleys and study an example where SSWM outperforms the (1+1) EA by taking advantage of information on the fitness gradient.},
author = {Paixao, Tiago and Sudholt, Dirk and Heredia, Jorge and Trubenova, Barbora},
booktitle = {Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation},
location = {Madrid, Spain},
pages = {1455 -- 1462},
publisher = {ACM},
title = {{First steps towards a runtime comparison of natural and artificial evolution}},
doi = {10.1145/2739480.2754758},
year = {2015},
}
@misc{1473,
abstract = {In this paper we survey geometric and arithmetic techniques to study the cohomology of semiprojective hyperkähler manifolds including toric hyperkähler varieties, Nakajima quiver varieties and moduli spaces of Higgs bundles on Riemann surfaces. The resulting formulae for their Poincaré polynomials are combinatorial and representation theoretical in nature. In particular we will look at their Betti numbers and will establish some results and state some expectations on their asymptotic shape.},
author = {Tamas Hausel and Rodríguez Villegas, Fernando},
booktitle = {Asterisque},
number = {370},
pages = {113 -- 156},
publisher = {Societe Mathematique de France},
title = {{Cohomology of large semiprojective hyperkähler varieties}},
volume = {2015},
year = {2015},
}
@inproceedings{1474,
abstract = {Cryptographic access control offers selective access to encrypted data via a combination of key management and functionality-rich cryptographic schemes, such as attribute-based encryption. Using this approach, publicly available meta-data may inadvertently leak information on the access policy that is enforced by cryptography, which renders cryptographic access control unusable in settings where this information is highly sensitive. We begin to address this problem by presenting rigorous definitions for policy privacy in cryptographic access control. For concreteness we set our results in the model of Role-Based Access Control (RBAC), where we identify and formalize several different flavors of privacy, however, our framework should serve as inspiration for other models of access control. Based on our insights we propose a new system which significantly improves on the privacy properties of state-of-the-art constructions. Our design is based on a novel type of privacy-preserving attribute-based encryption, which we introduce and show how to instantiate. We present our results in the context of a cryptographic RBAC system by Ferrara et al. (CSF'13), which uses cryptography to control read access to files, while write access is still delegated to trusted monitors. We give an extension of the construction that permits cryptographic control over write access. Our construction assumes that key management uses out-of-band channels between the policy enforcer and the users but eliminates completely the need for monitoring read/write access to the data.},
author = {Ferrara, Anna and Fuchsbauer, Georg and Liu, Bin and Warinschi, Bogdan},
location = {Verona, Italy},
pages = {46--60},
publisher = {IEEE},
title = {{Policy privacy in cryptographic access control}},
doi = {10.1109/CSF.2015.11},
year = {2015},
}
@inproceedings{1481,
abstract = {Simple board games, like Tic-Tac-Toe and CONNECT-4, play an important role not only in the development of mathematical and logical skills, but also in the emotional and social development. In this paper, we address the problem of generating targeted starting positions for such games. This can facilitate new approaches for bringing novice players to mastery, and also leads to discovery of interesting game variants. We present an approach that generates starting states of varying hardness levels for player 1 in a two-player board game, given rules of the board game, the desired number of steps required for player 1 to win, and the expertise levels of the two players. Our approach leverages symbolic methods and iterative simulation to efficiently search the extremely large state space. We present experimental results that include discovery of states of varying hardness levels for several simple grid-based board games. The presence of such states for standard game variants like 4×4 Tic-Tac-Toe opens up new games to be played that have never been played as the default start state is heavily biased. },
author = {Ahmed, Umair and Chatterjee, Krishnendu and Gulwani, Sumit},
booktitle = {Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence},
location = {Austin, TX, USA},
pages = {745 -- 752},
publisher = {AAAI Press},
title = {{Automatic generation of alternative starting positions for simple traditional board games}},
volume = {2},
year = {2015},
}
@inproceedings{1483,
abstract = {Topological data analysis offers a rich source of valuable information to study vision problems. Yet, so far we lack a theoretically sound connection to popular kernel-based learning techniques, such as kernel SVMs or kernel PCA. In this work, we establish such a connection by designing a multi-scale kernel for persistence diagrams, a stable summary representation of topological features in data. We show that this kernel is positive definite and prove its stability with respect to the 1-Wasserstein distance. Experiments on two benchmark datasets for 3D shape classification/retrieval and texture recognition show considerable performance gains of the proposed method compared to an alternative approach that is based on the recently introduced persistence landscapes.},
author = {Reininghaus, Jan and Huber, Stefan and Bauer, Ulrich and Kwitt, Roland},
location = {Boston, MA, USA},
pages = {4741 -- 4748},
publisher = {IEEE},
title = {{A stable multi-scale kernel for topological machine learning}},
doi = {10.1109/CVPR.2015.7299106},
year = {2015},
}
@inproceedings{1495,
abstract = {Motivated by biological questions, we study configurations of equal-sized disks in the Euclidean plane that neither pack nor cover. Measuring the quality by the probability that a random point lies in exactly one disk, we show that the regular hexagonal grid gives the maximum among lattice configurations. },
author = {Edelsbrunner, Herbert and Iglesias Ham, Mabel and Kurlin, Vitaliy},
booktitle = {Proceedings of the 27th Canadian Conference on Computational Geometry},
location = {Ontario, Canada},
pages = {128--135},
publisher = {Queen's University},
title = {{Relaxed disk packing}},
volume = {2015-August},
year = {2015},
}
@article{1497,
abstract = {Detecting allelic biases from high-throughput sequencing data requires an approach that maximises sensitivity while minimizing false positives. Here, we present Allelome.PRO, an automated user-friendly bioinformatics pipeline, which uses high-throughput sequencing data from reciprocal crosses of two genetically distinct mouse strains to detect allele-specific expression and chromatin modifications. Allelome.PRO extends approaches used in previous studies that exclusively analyzed imprinted expression to give a complete picture of the ‘allelome’ by automatically categorising the allelic expression of all genes in a given cell type into imprinted, strain-biased, biallelic or non-informative. Allelome.PRO offers increased sensitivity to analyze lowly expressed transcripts, together with a robust false discovery rate empirically calculated from variation in the sequencing data. We used RNA-seq data from mouse embryonic fibroblasts from F1 reciprocal crosses to determine a biologically relevant allelic ratio cutoff, and define for the first time an entire allelome. Furthermore, we show that Allelome.PRO detects differential enrichment of H3K4me3 over promoters from ChIP-seq data validating the RNA-seq results. This approach can be easily extended to analyze histone marks of active enhancers, or transcription factor binding sites and therefore provides a powerful tool to identify candidate cis regulatory elements genome wide.},
author = {Andergassen, Daniel and Dotter, Christoph and Kulinski, Tomasz and Guenzl, Philipp and Bammer, Philipp and Barlow, Denise and Pauler, Florian and Hudson, Quanah},
journal = {Nucleic Acids Research},
number = {21},
publisher = {Oxford University Press},
title = {{Allelome.PRO, a pipeline to define allele-specific genomic features from high-throughput sequencing data}},
doi = {10.1093/nar/gkv727},
volume = {43},
year = {2015},
}
@inproceedings{1498,
abstract = {Fault-tolerant distributed algorithms play an important role in many critical/high-availability applications. These algorithms are notoriously difficult to implement correctly, due to asynchronous communication and the occurrence of faults, such as the network dropping messages or computers crashing. Nonetheless there is surprisingly little language and verification support to build distributed systems based on fault-tolerant algorithms. In this paper, we present some of the challenges that a designer has to overcome to implement a fault-tolerant distributed system. Then we review different models that have been proposed to reason about distributed algorithms and sketch how such a model can form the basis for a domain-specific programming language. Adopting a high-level programming model can simplify the programmer's life and make the code amenable to automated verification, while still compiling to efficiently executable code. We conclude by summarizing the current status of an ongoing language design and implementation project that is based on this idea.},
author = {Dragoi, Cezara and Henzinger, Thomas A and Zufferey, Damien},
isbn = {978-3-939897-80-4 },
location = {Asilomar, CA, United States},
pages = {90 -- 102},
publisher = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
title = {{The need for language support for fault-tolerant distributed systems}},
doi = {10.4230/LIPIcs.SNAPL.2015.90},
volume = {32},
year = {2015},
}
@inproceedings{1499,
abstract = {We consider weighted automata with both positive and negative integer weights on edges and
study the problem of synchronization using adaptive strategies that may only observe whether
the current weight-level is negative or nonnegative. We show that the synchronization problem is decidable in polynomial time for deterministic weighted automata.},
author = {Kretinsky, Jan and Larsen, Kim and Laursen, Simon and Srba, Jiří},
location = {Madrid, Spain},
pages = {142 -- 154},
publisher = {Schloss Dagstuhl - Leibniz-Zentrum für Informatik},
title = {{Polynomial time decidability of weighted synchronization under partial observability}},
doi = {10.4230/LIPIcs.CONCUR.2015.142},
volume = {42},
year = {2015},
}
@misc{1500,
abstract = {In this poster, we present methods for randomly generating hybrid automata with affine differential equations, invariants, guards, and assignments. Selecting an arbitrary affine function from the set of all affine functions results in a low likelihood of generating hybrid automata with diverse and interesting behaviors, as there are an uncountable number of elements in the set of all affine functions. Instead, we partition the set of all affine functions into potentially interesting classes and randomly select elements from these classes. For example, we partition the set of all affine differential equations by using restrictions on eigenvalues such as those that yield stable, unstable, etc. equilibrium points. We partition the components describing discrete behavior (guards, assignments, and invariants) to allow either time-dependent or state-dependent switching, and in particular provide the ability to generate subclasses of piecewise-affine hybrid automata. Our preliminary experimental results with a prototype tool called HyRG (Hybrid Random Generator) illustrate the feasibility of this generation method to automatically create standard hybrid automaton examples like the bouncing ball and thermostat.},
author = {Nguyen, Luan V and Christian Schilling and Sergiy Bogomolov and Johnson, Taylor T},
booktitle = {HSCC: Hybrid Systems - Computation and Control},
pages = {289 -- 290},
publisher = {Springer},
title = {{Poster: HyRG: A random generation tool for affine hybrid automata}},
doi = {10.1145/2728606.2728650},
year = {2015},
}
@article{1501,
abstract = {We consider Markov decision processes (MDPs) which are a standard model for probabilistic systems. We focus on qualitative properties for MDPs that can express that desired behaviors of the system arise almost-surely (with probability 1) or with positive probability. We introduce a new simulation relation to capture the refinement relation of MDPs with respect to qualitative properties, and present discrete graph algorithms with quadratic complexity to compute the simulation relation. We present an automated technique for assume-guarantee style reasoning for compositional analysis of two-player games by giving a counterexample guided abstraction-refinement approach to compute our new simulation relation. We show a tight link between two-player games and MDPs, and as a consequence the results for games are lifted to MDPs with qualitative properties. We have implemented our algorithms and show that the compositional analysis leads to significant improvements. },
author = {Chatterjee, Krishnendu and Chmelik, Martin and Daca, Przemyslaw},
journal = {Formal Methods in System Design},
number = {2},
pages = {230 -- 264},
publisher = {Springer},
title = {{CEGAR for compositional analysis of qualitative properties in Markov decision processes}},
doi = {10.1007/s10703-015-0235-2},
volume = {47},
year = {2015},
}
@inproceedings{1502,
abstract = {We extend the theory of input-output conformance with operators for merge and quotient. The former is useful when testing against multiple requirements or views. The latter can be used to generate tests for patches of an already tested system. Both operators can combine systems with different action alphabets, which is usually the case when constructing complex systems and specifications from parts, for instance different views as well as newly defined functionality of a~previous version of the system.},
author = {Beneš, Nikola and Daca, Przemyslaw and Henzinger, Thomas A and Kretinsky, Jan and Nickovic, Dejan},
isbn = {978-1-4503-3471-6},
location = {Montreal, QC, Canada},
pages = {101 -- 110},
publisher = {ACM},
title = {{Complete composition operators for IOCO-testing theory}},
doi = {10.1145/2737166.2737175},
year = {2015},
}
@article{1503,
abstract = {A Herman-Avila-Bochi type formula is obtained for the average sum of the top d Lyapunov exponents over a one-parameter family of double-struck G-cocycles, where double-struck G is the group that leaves a certain, non-degenerate Hermitian form of signature (c, d) invariant. The generic example of such a group is the pseudo-unitary group U(c, d) or, in the case c = d, the Hermitian-symplectic group HSp(2d) which naturally appears for cocycles related to Schrödinger operators. In the case d = 1, the formula for HSp(2d) cocycles reduces to the Herman-Avila-Bochi formula for SL(2, ℝ) cocycles.},
author = {Sadel, Christian},
journal = {Ergodic Theory and Dynamical Systems},
number = {5},
pages = {1582 -- 1591},
publisher = {Cambridge University Press},
title = {{A Herman-Avila-Bochi formula for higher-dimensional pseudo-unitary and Hermitian-symplectic-cocycles}},
doi = {10.1017/etds.2013.103},
volume = {35},
year = {2015},
}
@article{1504,
abstract = {Let Q = (Q1, . . . , Qn) be a random vector drawn from the uniform distribution on the set of all n! permutations of {1, 2, . . . , n}. Let Z = (Z1, . . . , Zn), where Zj is the mean zero variance one random variable obtained by centralizing and normalizing Qj , j = 1, . . . , n. Assume that Xi , i = 1, . . . ,p are i.i.d. copies of 1/√ p Z and X = Xp,n is the p × n random matrix with Xi as its ith row. Then Sn = XX is called the p × n Spearman's rank correlation matrix which can be regarded as a high dimensional extension of the classical nonparametric statistic Spearman's rank correlation coefficient between two independent random variables. In this paper, we establish a CLT for the linear spectral statistics of this nonparametric random matrix model in the scenario of high dimension, namely, p = p(n) and p/n→c ∈ (0,∞) as n→∞.We propose a novel evaluation scheme to estimate the core quantity in Anderson and Zeitouni's cumulant method in [Ann. Statist. 36 (2008) 2553-2576] to bypass the so-called joint cumulant summability. In addition, we raise a two-step comparison approach to obtain the explicit formulae for the mean and covariance functions in the CLT. Relying on this CLT, we then construct a distribution-free statistic to test complete independence for components of random vectors. Owing to the nonparametric property, we can use this test on generally distributed random variables including the heavy-tailed ones.},
author = {Bao, Zhigang and Lin, Liang and Pan, Guangming and Zhou, Wang},
journal = {Annals of Statistics},
number = {6},
pages = {2588 -- 2623},
publisher = {Institute of Mathematical Statistics},
title = {{Spectral statistics of large dimensional spearman s rank correlation matrix and its application}},
doi = {10.1214/15-AOS1353},
volume = {43},
year = {2015},
}
@article{1505,
abstract = {This paper is aimed at deriving the universality of the largest eigenvalue of a class of high-dimensional real or complex sample covariance matrices of the form W N =Σ 1/2XX∗Σ 1/2 . Here, X = (xij )M,N is an M× N random matrix with independent entries xij , 1 ≤ i M,≤ 1 ≤ j ≤ N such that Exij = 0, E|xij |2 = 1/N . On dimensionality, we assume that M = M(N) and N/M → d ε (0, ∞) as N ∞→. For a class of general deterministic positive-definite M × M matrices Σ , under some additional assumptions on the distribution of xij 's, we show that the limiting behavior of the largest eigenvalue of W N is universal, via pursuing a Green function comparison strategy raised in [Probab. Theory Related Fields 154 (2012) 341-407, Adv. Math. 229 (2012) 1435-1515] by Erd″os, Yau and Yin for Wigner matrices and extended by Pillai and Yin [Ann. Appl. Probab. 24 (2014) 935-1001] to sample covariance matrices in the null case (&Epsi = I ). Consequently, in the standard complex case (Ex2 ij = 0), combing this universality property and the results known for Gaussian matrices obtained by El Karoui in [Ann. Probab. 35 (2007) 663-714] (nonsingular case) and Onatski in [Ann. Appl. Probab. 18 (2008) 470-490] (singular case), we show that after an appropriate normalization the largest eigenvalue of W N converges weakly to the type 2 Tracy-Widom distribution TW2 . Moreover, in the real case, we show that whenΣ is spiked with a fixed number of subcritical spikes, the type 1 Tracy-Widom limit TW1 holds for the normalized largest eigenvalue of W N , which extends a result of Féral and Péché in [J. Math. Phys. 50 (2009) 073302] to the scenario of nondiagonal Σ and more generally distributed X . In summary, we establish the Tracy-Widom type universality for the largest eigenvalue of generally distributed sample covariance matrices under quite light assumptions on &Sigma . Applications of these limiting results to statistical signal detection and structure recognition of separable covariance matrices are also discussed.},
author = {Bao, Zhigang and Pan, Guangming and Zhou, Wang},
journal = {Annals of Statistics},
number = {1},
pages = {382 -- 421},
publisher = {Institute of Mathematical Statistics},
title = {{Universality for the largest eigenvalue of sample covariance matrices with general population}},
doi = {10.1214/14-AOS1281},
volume = {43},
year = {2015},
}
@article{1506,
abstract = {Consider the square random matrix An = (aij)n,n, where {aij:= a(n)ij , i, j = 1, . . . , n} is a collection of independent real random variables with means zero and variances one. Under the additional moment condition supn max1≤i,j ≤n Ea4ij <∞, we prove Girko's logarithmic law of det An in the sense that as n→∞ log | detAn| ? (1/2) log(n-1)! d/→√(1/2) log n N(0, 1).},
author = {Bao, Zhigang and Pan, Guangming and Zhou, Wang},
journal = {Bernoulli},
number = {3},
pages = {1600 -- 1628},
publisher = {Bernoulli Society for Mathematical Statistics and Probability},
title = {{The logarithmic law of random determinant}},
doi = {10.3150/14-BEJ615},
volume = {21},
year = {2015},
}