Zobrazeno 11 - 20
of 1 210
pro vyhledávání: '"Corander, Jukka"'
Cluster visualization is an essential task for nonlinear dimensionality reduction as a data analysis tool. It is often believed that Student t-Distributed Stochastic Neighbor Embedding (t-SNE) can show clusters for well clusterable data, with a small
Externí odkaz:
http://arxiv.org/abs/2110.02573
Neighbor Embedding (NE) aims to preserve pairwise similarities between data items and has been shown to yield an effective principle for data visualization. However, even the best existing NE methods such as Stochastic Neighbor Embedding (SNE) may le
Externí odkaz:
http://arxiv.org/abs/2108.08003
Autor:
Järvenpää, Marko, Corander, Jukka
We present a framework for approximate Bayesian inference when only a limited number of noisy log-likelihood evaluations can be obtained due to computational constraints, which is becoming increasingly common for applications of complex models. We mo
Externí odkaz:
http://arxiv.org/abs/2104.03942
Publikováno v:
Scandinavian Journal of Statistics, Vol. 44: 455-479, 2017
Markov networks are popular models for discrete multivariate systems where the dependence structure of the variables is specified by an undirected graph. To allow for more expressive dependence structures, several generalizations of Markov networks h
Externí odkaz:
http://arxiv.org/abs/2103.15540
Autor:
Pöntinen, Anna K, Gladstone, Rebecca A, Pesonen, Henri, Pesonen, Maiju, Cléon, François, Parcell, Benjamin J, Kallonen, Teemu, Simonsen, Gunnar Skov, Croucher, Nicholas J, McNally, Alan, Parkhill, Julian, Johnsen, Pål J, Samuelsen, Ørjan, Corander, Jukka
Publikováno v:
In The Lancet Microbe February 2024 5(2):e142-e150
Publikováno v:
Stat Comput 31, 73 (2021)
Learning vector autoregressive models from multivariate time series is conventionally approached through least squares or maximum likelihood estimation. These methods typically assume a fully connected model which provides no direct insight to the mo
Externí odkaz:
http://arxiv.org/abs/2011.01484
A stream of algorithmic advances has steadily increased the popularity of the Bayesian approach as an inference paradigm, both from the theoretical and applied perspective. Even with apparent successes in numerous application fields, a rising concern
Externí odkaz:
http://arxiv.org/abs/2007.04358
In recent years, surrogate models have been successfully used in likelihood-free inference to decrease the number of simulator evaluations. The current state-of-the-art performance for this task has been achieved by Bayesian Optimization with Gaussia
Externí odkaz:
http://arxiv.org/abs/2006.10571
Synthetic likelihood (SL) is a strategy for parameter inference when the likelihood function is analytically or computationally intractable. In SL, the likelihood function of the data is replaced by a multivariate Gaussian density over summary statis
Externí odkaz:
http://arxiv.org/abs/2004.04558
We present a new method for probabilistic elicitation of expert knowledge using binary responses of human experts assessing simulated data from a statistical model, where the parameters are subject to uncertainty. The binary responses describe either
Externí odkaz:
http://arxiv.org/abs/2002.10902