Filters








6,022 Hits in 3.3 sec

Robust information divergences for model-form uncertainty arising from sparse data in random PDE [article]

Eric Joseph Hall, Markos A. Katsoulakis
2018 arXiv   pre-print
We develop a novel application of hybrid information divergences to analyze uncertainty in steady-state subsurface flow problems.  ...  These hybrid information divergences are non-intrusive, goal-oriented uncertainty quantification tools that enable robust, data-informed predictions in support of critical decision tasks such as regulatory  ...  dimensional family that includes both parametric and non-parametric perturbations.  ... 
arXiv:1708.03718v2 fatcat:uavfwywalrfjnj4yjwbj2hspky

Inference using phi-divergence Goodness-of-Fit tests

Nikhil Kundargi, Ahmed Tewfik
2012 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
We show that under uncertainty or non-gaussianity in the noise, the performance of non-parametric tests in general, and phi-divergence based goodnessof-fit tests in particular, is significantly superior  ...  In this paper we study the inferential use of goodness of fit tests in a non-parametric setting.  ...  We will use these generalizations to come up with a powerful family of goodness of fit statistics. In this paper, we propose the following a) A generalized framework based on phi-divergences.  ... 
doi:10.1109/icassp.2012.6288546 dblp:conf/icassp/KundargiT12 fatcat:jg6wlohbdvf2tcqtsnlni4bgfa

Robust Procedures for Estimating and Testing in the Framework of Divergence Measures

Leandro Pardo, Nirian Martín
2021 Entropy  
The approach for estimating and testing based on divergence measures has become, in the last 30 years, a very popular technique not only in the field of statistics, but also in other areas, such as machine  ...  the non-parametric run length test of equality of distributions.  ...  In "Robust Change Point Test for General Integer-Valued Time Series Models Based on Density Power Divergence" by Kim and Lee [24] , the problem of testing for a parameter change in general integer-valued  ... 
doi:10.3390/e23040430 pmid:33917362 fatcat:ud3szi5mbnhznodwwvog245bva

A computational intelligence-based criterion to detect non-stationarity trends

C. Alippi, M. Roveri
2006 The 2006 IEEE International Joint Conference on Neural Network Proceedings  
More specifically, we suggest a robust extension of the adaptive CUSUM test procedure which addresses a set of features (in contrast to the literature which considers a single feature) for detecting drifts  ...  The application of the change detection test to real applications shows that its real additional value resides in the ability to detect continuous and small drifts, a critical situation for traditional  ...  Such tests can be divided into two main families: parametric and non-parametric.  ... 
doi:10.1109/ijcnn.2006.247230 dblp:conf/ijcnn/AlippiR06 fatcat:zixi7yji6nclhgyeuu7amopuym

Convex Cauchy Schwarz Independent Component Analysis for Blind Source Separation [article]

Zaid Albataineh, Fathi M. Salem
2014 arXiv   pre-print
With this measure, a new CCS ICA algorithm is structured and a non parametric form is developed incorporating the Parzen window based distribution.  ...  We present two schemes of pairwise non parametric ICA algorithms, one is based on gradient decent and the second on the Jacobi Iterative method.  ...  A novel family of dependency divergence is developed which we name Convex Cauchy Schwarz Divergence (CCS-DIV) --due to its use of the Cauchy Schwarz Inequality "divergence."  ... 
arXiv:1408.0192v1 fatcat:rkalcmzk2ff5zfu7jrvlnwk2my

Linearly Constrained Gaussian Processes with Boundary Conditions [article]

Markus Lange-Hegermann
2021 arXiv   pre-print
It builds these priors combining two parametrizations via a pullback: the first parametrizes the solutions for the system of differential equations and the second parametrizes all functions adhering to  ...  We construct multi-output Gaussian process priors with realizations in the solution set of such systems, in particular only such solutions can be represented by Gaussian process regression.  ...  It presents a novel framework to 1. describe parametrizations for boundary conditions, 2. combine parametrizations by intersecting their images, and 3. build Gaussian process priors with realizations in  ... 
arXiv:2002.00818v3 fatcat:6nmv5k4nyvhxzb7p2bztvmpgbi

Bayesian Neural Hawkes Process for Event Uncertainty Prediction [article]

Manisha Dubey, Ragja Palakkadavath, P.K. Srijith
2022 arXiv   pre-print
Therefore, we propose a novel point process model, Bayesian Neural Hawkes process (BNHP) which leverages uncertainty modelling capability of Bayesian models and generalization capability of the neural  ...  Recent works have introduced neural network based point processes for modeling event-times, and were shown to provide state-of-the-art performance in predicting event-times.  ...  A popular tool for modeling event-based data is point process and is defined using an underlying intensity function.  ... 
arXiv:2112.14474v2 fatcat:omhl7crmovcxvnfgsfwjrx3pha

A Convex Cauchy-Schwarz DivergenceMeasure for Blind Source Separation [article]

Zaid Albataineh, Fathi M. Salem
2016 arXiv   pre-print
We propose a new class of divergence measures for Independent Component Analysis (ICA) for the demixing of multiple source mixtures.  ...  An algorithm, generated from the proposed divergence, is developed which is employing the non-parametric Parzen window-based distribution.  ...  We note that the performance of a learning algorithm based on the non-parametric ICA is better than the performance of a learning algorithm based on the parametric ICA.  ... 
arXiv:1604.04666v1 fatcat:kmvnobdnyfg2nioatusd35jdgi

A Parametric Empirical Bayes Model to Predict Software Reliability Growth

Néstor R. Barraza
2015 Procedia Computer Science  
Instead of a non homogeneous in time failure rate as it is usually used to model reliability growth, a failure rate depending non linearly on the previous number of failures is obtained from our model.  ...  A new software reliability model based on the empirical Bayes estimate is developed.  ...  Acknowledgments This work was supported by Universidad Nacional de Tres de Febrero, Caseros, under Grant No. 62 "Análisis de Modelos Estadísticos aplicados a Confiabilidad, Programacin en la nube, Compresión  ... 
doi:10.1016/j.procs.2015.08.416 fatcat:b3f6oo3ijvfqbf2m7gbnkiqpki

On Hölder Projective Divergences

Frank Nielsen, Ke Sun, Stéphane Marchand-Maillet
2017 Entropy  
We report closed-form formulas for those statistical dissimilarities when considering distributions belonging to the same exponential family provided that the natural parameter space is a cone (e.g., multivariate  ...  Finally, we show how to compute statistical H\"older centroids with respect to those divergences, and carry out center-based clustering toy experiments on a set of Gaussian distributions that demonstrate  ...  Acknowledgments: The authors gratefully thank the referees for their comments. Ke Sun is funded by King Abdullah University of Science and Technology (KAUST).  ... 
doi:10.3390/e19030122 fatcat:tht5h3is5ffz3cwu3cdtgjwzle

A generalization of the Jensen divergence: The chord gap divergence [article]

Frank Nielsen
2017 arXiv   pre-print
We introduce a novel family of distances, called the chord gap divergences, that generalizes the Jensen divergences (also called the Burbea-Rao distances), and study its properties.  ...  remainder form of the skew Jensen divergences.  ...  a strictly real-valued convex function F : J F (p, q) = F (p) + F (q) 2 − F p + q 2 . (2) We can extend the Jensen divergence to a parametric family of skew Jensen divergences J α F (with α ∈ (0, 1)) built  ... 
arXiv:1709.10498v2 fatcat:3wq4hmschnfzljzak3nqfhp6ja

Familial Risk and Heritability of Hematologic Malignancies in the Nordic Twin Study of Cancer

Signe B. Clemmensen, Jennifer R. Harris, Jonas Mengel-From, Wagner H. Bonat, Henrik Frederiksen, Jaakko Kaprio, Jacob v. B. Hjelmborg
2021 Cancers  
We estimated the cumulative incidence by age, familial risk, and genetic and environmental variance components of hematologic malignancies accounting for competing risk of death.  ...  The study base included 316,397 individual twins from the Nordic Twin Study of Cancer with a median of 41 years of follow-up: 88,618 (28%) of the twins were monozygotic, and 3459 hematologic malignancies  ...  Acknowledgments: The authors are thankful to The Danish Twin Registry for hosting and managing the joint Nordic twin data.  ... 
doi:10.3390/cancers13123023 fatcat:f5qfy77s3ncfxfjiit7jrnv4ki

Environmental fluctuations do not select for increased variation or population-based resistance inEscherichia coli [article]

Shraddha Madhav Karve, Kanishka Tiwary, S Selveshwari, Sutirth Dey
2015 bioRxiv   pre-print
Our results also underline the need for a very different kind of theoretical approach to study the effects of fluctuating environments.  ...  More importantly, there were no outliers in terms of growth, thus ruling out the evolution of population-based resistance.  ...  SK was supported by a Senior Research Fellowship from Council of Scientific and Industrial Research, Govt. of India.  ... 
doi:10.1101/021030 fatcat:z7sqaqmbsffppp322gsgqqt7za

Environmental fluctuations do not select for increased variation or population-based resistance in Escherichia coli

Shraddha Madhav Karve, Kanishka Tiwary, S Selveshwari, Sutirth Dey
2016 Journal of Biosciences  
Our results also underline the need for a very different kind of theoretical approach to study the effects of fluctuating environments.  ...  More importantly, there were no outliers in terms of growth, thus ruling out the evolution of population-based resistance.  ...  SK was supported by a Senior Research Fellowship from Council of Scientific and Industrial Research, Govt. of India.  ... 
doi:10.1007/s12038-016-9592-2 pmid:26949086 fatcat:v4zmtqw6rndwjpdxjtimpszwfy

Cramer-Rao Lower Bound and Information Geometry [article]

Frank Nielsen
2013 arXiv   pre-print
Rao (25 years old then) published a pathbreaking paper, which had a profound impact on subsequent statistical research.  ...  This article focuses on an important piece of work of the world renowned Indian statistician, Calyampudi Radhakrishna Rao. In 1945, C. R.  ...  Loosely speaking, a geometric parametric statistical manifold F = {p θ (x)|θ ∈ Θ} equipped with a f -divergence must also provide invariance by: Non-singular parameter reparameterization.  ... 
arXiv:1301.3578v2 fatcat:yil27icpcfb5xk7bh4enytemqi
« Previous Showing results 1 — 15 out of 6,022 results