@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{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}, } @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}, } @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{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{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}, } @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{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}, } @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{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}, }