G-SVGD modifies SVGD with a loss-based line search and a KDE-based local Gaussian approximation, but the convergence claims are not backed by independent validation.
MaxEntropy Pursuit Variational Inference
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
One of the core problems in variational inference is a choice of approximate posterior distribution. It is crucial to trade-off between efficient inference with simple families as mean-field models and accuracy of inference. We propose a variant of a greedy approximation of the posterior distribution with tractable base learners. Using Max-Entropy approach, we obtain a well-defined optimization problem. We demonstrate the ability of the method to capture complex multimodal posterior via continual learning setting for neural networks.
fields
stat.CO 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Greedy Stein Variational Gradient Descent: An algorithmic approach for wave prospection problems
G-SVGD modifies SVGD with a loss-based line search and a KDE-based local Gaussian approximation, but the convergence claims are not backed by independent validation.