A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is
Due to the halting problem, however, this notion is not computable. We hence propose to do causal inference by stochastic complexity. ... We instantiate this framework, which we call CISC, for pairs of univariate discrete variables, using the class of multinomial distributions. ... For this class the stochastic complexity is computable remarkably e ciently, by which our score has only a linear-time computational complexity. rough experiments we show that our method, , for causal ...arXiv:1702.06776v1 fatcat:ngerxllnaffmdil5zupcohugmy
To address this problem, we propose augment and reduce (A&R), a method to alleviate the computational complexity. ... A&R uses two ideas: latent variable augmentation and stochastic variational inference. It maximizes a lower bound on the marginal likelihood of the data. ... Ruiz is supported by the EU Horizon 2020 programme (Marie Skłodowska-Curie Individual Fellowship, grant agreement 706760). We also thank Victor Elvira and Pablo Moreno for their comments and help. ...arXiv:1802.04220v3 fatcat:nopyq4p4znfbfkd4syeqp2paiu
2008 International Symposium on Information Theory and Its Applications
Utilizing this framework, we derive a new recurrence relation over the values of a multinomial variable, and show how to apply the recurrence for computing the stochastic complexity. ... There now exists new efficient computation methods, based on generating functions, for computing the stochastic complexity in the multinomial case. ... This work was supported in part by the Academy of Finland under the project Civi and by the Finnish Funding Agency for Technology and Innovation under the projects Kukot and PMMA. ...doi:10.1109/isita.2008.4895423 fatcat:p7yf7qvzgzbjncxythdl66dite
Myllymäki, A linear-time algorithm for computing the multinomial stochastic complexity. Information Processing Letters 103 (2007) 6 (September), 227-233. 3.9. ... Myllymäki, Computing the Multinomial Stochastic Complexity in Sub-Linear Time. Pp. 209-216 in Proceedings of the 4th European Workshop on Probabilistic Graphical Models (PGM-08), edited by M. ...doi:10.1007/s11042-010-0562-7 fatcat:gkj2f54acvg27jv55vyqydjypi
In this paper, we first review some existing algorithms for efficient NML computation in the case of multinomial and naive Bayes model families. ... In the case of discrete data, straightforward computation of the NML distribution requires exponential time with respect to the sample size, since the definition involves a sum over all the possible data ... ACKNOWLEDGMENTS The authors would like to thank the anonymous reviewers and Jorma Rissanen for useful comments. ...doi:10.1155/2007/90947 pmid:18382603 pmcid:PMC3171356 fatcat:nz2acyrz4fce3oisxm2hwdyj5u
A two-stage computational (2-point exchange and Newton-type) algorithm for finding the optimal Latin hypercube design is pre- sented. ... Summary: “A family of one-dimensional linear stochastic approx- imation procedures in continuous time, where the error processes are Gaussian martingales, is considered. ...
For sparse polynomials the Simp algorithm multiplies using a simple divide and conquer approach, and the NOMC algorithm computes powers using a multinomial expansion. ... By replacing the universal computer by a class of probabilistic models the author modifies the algorithmic notion of complexity and calls the new measure the stochastic complexity of the data, relative ...
The proposed algorithm is used to compute the estimator of a time-series model. ... A learning algorithm for optimizing time-and frequency-resolution pursuits is described. Murat K. ...doi:10.1016/s0167-9473(02)00350-x fatcat:jm2ewom3hnabdevnik42xxu6l4
Lecture Notes in Computer Science
As opposed to higher-order statistical models, our schemes require linear space complexity, and compress with nearly 10% better efficiency than the traditional adaptive coding methods. ... In this paper, we introduce a new approach to adaptive coding which utilizes Stochastic Learning-based Weak Estimation (SLWE) techniques to adaptively update the probabilities of the source symbols. ... The algorithm for updating the probabilities by using a nonlinear SLWE scheme is similar to the linear case, except that the updating rule is changed to be that of (3) and (4) in Algorithm Probability ...doi:10.1007/978-3-540-30198-1_24 fatcat:dketyqfs4beixl6wk3hc2hw33u
IEEE/SP 13th Workshop on Statistical Signal Processing, 2005
Numerical simulations show that the algorithm employing deterministic particle selection greatly outperforms alternative stochastic strategies, even when the latter employ the optimal importance function ... This work proposes deterministic particle filtering structures for joint blindly equalizing/decoding convolutionally coded signals transmitted over frequency selective channels. ... PARTICLE FILTERS Let y n denote the observed output at instant n of a possibly non-linear and time-varying stochastically driven system whose state variable x n we want to estimate. ...doi:10.1109/ssp.2005.1628624 fatcat:3zkgrdr36nbchl7alo6ptmbdzq
The manifolds, called the doubly stochastic, symmetric and the definite multinomial manifolds, generalize the simplex also known as the multinomial manifold. ... On the other hand, optimization algorithms on manifold have shown great ability in finding solutions to nonconvex problems in reasonable time. ... TABLE I COMPLEXITY I OF THE STEEPEST DESCENT AND NEWTON'S METHOD ALGORITHMS FOR THE PROPOSED MANIFOLDS. ...arXiv:1802.02628v1 fatcat:4elildiw5rdbznrczfexmbza4y
One of the steps in our edge switch algorithm requires the computation of multinomial random variables in parallel. The paper presents the first non-trivial parallel algorithm for the problem. ... The growth of real-world networks motivates the need to develop efficient parallel algorithms for performing a large sequence of edge switch operations. ... Parallel Algorithm for Computing Multinomial Distribution Based on the conditional distributed method shown in Algorithm 4, we propose a parallel algorithm for computing multinomial distribution X ∼ M ...doi:10.1109/icpp.2014.15 dblp:conf/icpp/BhuiyanCKM14 fatcat:mq7tdop57vbrjertkn5p73vpuu
Physical Review A
The method enables stochastic sampling of the Liouville-von-Neumann time evolution of the density matrix, thanks to a massively parallel algorithm, thus providing estimates of observables on the non-equilibrium ... We develop a real-time Full Configuration Interaction Quantum Monte Carlo approach for the modeling of driven-dissipative open quantum systems. ... We are indebted to Hugo Flayac for having provided the MCWF simulations used to benchmark the present results. ...doi:10.1103/physreva.97.052129 fatcat:yt6zlu7debcynnpdmjqcigrzfq
In this paper, we present a distributed stochastic gradient descent based optimization method (DS-MLR) for scaling up multinomial logistic regression problems to massive scale datasets without hitting ... This is primarily because one needs to compute the log-partition function on every data point. This makes distributing the computation hard. ... This is a proxy for the precision@k curve and gives a more closer indication of the predictive performance of a multinomial classification algorithm. ...arXiv:1604.04706v7 fatcat:xxcezmmqwngd3bkcvdwnao6avq
For the considered benchmark datasets, the linear SVC has outperformed other classifiers overall when prominent features are selected. ... The overall classification evaluation results are compared using different classifiers such as multinomial Naive Bayes (MNB), Bernoulli Naive Bayes (BNB), Stochastic Gradient Descent (SGD), Support Vector ... Acknowledgments is research was supported by the Researchers Supporting Project number (RSP-2021/244), King Saud University, Riyadh, Saudi Arabia. ...doi:10.1155/2022/3720358 fatcat:wmqfo6l4krd3zkrrkivdawjcae
« Previous Showing results 1 — 15 out of 9,505 results