Maximum smoothed likelihood for multivariate mixtures
By Michael Levine, David R. Hunter, Didier Chauveau. 2011
76 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Statistics and Probability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernhard Schölkopf
- Dominik Janzing
- Jan Peters
- Eleni Sgouritsa
- Kun Zhang
- David Lopez-Paz
- Yoshua Bengio
- Sergey Levine
In Statistics and Probability
- Bernhard Schölkopf
- Dominik Janzing
- Jan Peters
- Eleni Sgouritsa
- Didier Chauveau
- Katsumi Shimotsu
- Hiroyuki Kasahara
- Michael Levine
Citations in the corpus
- Identifying Finite Mixtures of Nonparametric Product Distributions and Causal Inference of Confounders (2013, methodology): “Assuming model (1), Levine et al. (2011) proposed an Expectation-Maximization (EM) algorithm for nonparametric estimation of the parameters in (1), given that m is known.”
- Non‐parametric identification and estimation of the number of components in multivariate mixtures (2014, methodology): “Benaglia et al. (2009) and Levine et al. (2011) have developed algorithms for estimating model (1) nonparametrically by using kernels.”
- A Distributional Framework for Matched Employer Employee Data (2019, methodology): “Our approach to identification and estimation of mixture models has a number of precedents in the literature, such as Hall and Zhou (2003), Hu (2008), Henry et al. (2014), Levine et al. (2011), Bonhomme et al. (2014), and Hu and Schennach (2008) and Hu and Shum (2012) for continuous mixtures.”
- Semi-Parametric Estimation for Conditional Independence Multivariate Finite Mixture Models (2015, methodology): “[31] under the same assumptions we make here.”
- Inference in finite state space non parametric Hidden Markov Models and applications (2015, methodology): “Levine et al. (2011) proposes a very similar algorithm, based on the Majorization-Minimization principle, which converges to a local maximum of a smoothed likelihood.”
- Semiparametric mixtures of regressions (2012, methodology): “Nonetheless, using recent work of Levine, Hunter, and Chauveau (2011) and Chauveau, Hunter, and Levine (2010) as a guide, it is possible to adapt these algorithms slightly to produce a new algorithm that does increase the value of a smoothed version of the loglikelihood at each iteration.”