Search Results for author:
Found 9 papers, 2 papers with code
An Ordering of Divergences for Variational Inference with Factorized Gaussian Approximations
Our analysis covers the KL divergence, the R\'enyi divergences, and a score-based divergence that compares $\nabla\log p$ and $\nabla\log q$.
Batch and match: black-box variational inference with a score-based divergence
We analyze the convergence of BaM when the target distribution is Gaussian, and we prove that in the limit of infinite batch size the variational parameter updates converge exponentially quickly to the target mean and covariance.
The Shrinkage-Delinkage Trade-off: An Analysis of Factorized Gaussian Approximations for Variational Inference
We study various manifestations of this trade-off, notably one where, as the dimension of the problem grows, the per-component entropy gap between $p$ and $q$ becomes vanishingly small even though $q$ underestimates every componentwise variance by a constant multiplicative factor.
An online passive-aggressive algorithm for difference-of-squares classification
The model is also over-parameterized in the sense that different pairs of affine transformations can describe classifiers with the same decision boundary and confidence scores.
Topic Modeling of Hierarchical Corpora
We study the problem of topic modeling in corpora whose documents are organized in a multi-level hierarchy.
Latent Coincidence Analysis: A Hidden Variable Model for Distance Metric Learning
We describe a latent variable model for supervised dimensionality reduction and distance metric learning.
Maximum Covariance Unfolding : Manifold Learning for Bimodal Data
To perform this visualization, we augment MCU with an additional step for metric learning in the high dimensional voxel space.
Latent Variable Models for Predicting File Dependencies in Large-Scale Software Development
When software developers modify one or more files in a large code base, they must also identify and update other related files.
Kernel Methods for Deep Learning
We introduce a new family of positive-definite kernel functions that mimic the computation in large, multilayer neural nets.
