Challenges and opportunities in high dimensional variational inference
Current black-box variational inference (BBVI) methods require the user to make numerous
design choices–such as the selection of variational objective and approximating family–yet …
design choices–such as the selection of variational objective and approximating family–yet …
Variational inference via Wasserstein gradient flows
Abstract Along with Markov chain Monte Carlo (MCMC) methods, variational inference (VI)
has emerged as a central computational approach to large-scale Bayesian inference …
has emerged as a central computational approach to large-scale Bayesian inference …
Forward-backward Gaussian variational inference via JKO in the Bures-Wasserstein space
Variational inference (VI) seeks to approximate a target distribution $\pi $ by an element of a
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …
tractable family of distributions. Of key interest in statistics and machine learning is Gaussian …
On the convergence of black-box variational inference
We provide the first convergence guarantee for black-box variational inference (BBVI) with
the reparameterization gradient. While preliminary investigations worked on simplified …
the reparameterization gradient. While preliminary investigations worked on simplified …
The bayesian learning rule
We show that many machine-learning algorithms are specific instances of a single algorithm
called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide …
called the Bayesian learning rule. The rule, derived from Bayesian principles, yields a wide …
Towards understanding the dynamics of gaussian-stein variational gradient descent
T Liu, P Ghosal… - Advances in Neural …, 2024 - proceedings.neurips.cc
Abstract Stein Variational Gradient Descent (SVGD) is a nonparametric particle-based
deterministic sampling algorithm. Despite its wide usage, understanding the theoretical …
deterministic sampling algorithm. Despite its wide usage, understanding the theoretical …
Tractable structured natural-gradient descent using local parameterizations
Natural-gradient descent (NGD) on structured parameter spaces (eg, low-rank covariances)
is computationally challenging due to difficult Fisher-matrix computations. We address this …
is computationally challenging due to difficult Fisher-matrix computations. We address this …
Efficient, multimodal, and derivative-free bayesian inference with Fisher–Rao gradient flows
In this paper, we study efficient approximate sampling for probability distributions known up
to normalization constants. We specifically focus on a problem class arising in Bayesian …
to normalization constants. We specifically focus on a problem class arising in Bayesian …
Weight initialization based‐rectified linear unit activation function to improve the performance of a convolutional neural network model
Abstract Convolutional Neural Networks (CNNs) have made a great impact on attaining
state‐of‐the‐art results in image task classification. Weight initialization is one of the …
state‐of‐the‐art results in image task classification. Weight initialization is one of the …
Gradient flows for sampling: mean-field models, Gaussian approximations and affine invariance
Sampling a probability distribution with an unknown normalization constant is a fundamental
problem in computational science and engineering. This task may be cast as an optimization …
problem in computational science and engineering. This task may be cast as an optimization …