Search Results for author:
Found 3 papers, 0 papers with code
Kullback-Leibler Proximal Variational Inference
Secondly, we use the proximal framework to derive efficient variational algorithms for non-conjugate models.
Decoupled Variational Gaussian Inference
First, it maximizes a Lagrangian of the lower bound reducing the number of parameters to $O(N)$, where $N$ is the number of data examples.
Variational bounds for mixed-data factor analysis
We show that EM is significantly more robust in the presence of missing data compared to treating the latent factors as parameters, which is the approach used by exponential family PCA and other related matrix-factorization methods.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
