The Variational Predictive Natural Gradient
Variational inference transforms posterior inference into parametric optimization thereby enabling the use of latent variable models where otherwise impractical. However, variational inference can be finicky when different variational parameters control variables that are strongly correlated under the model. Traditional natural gradients based on the variational approximation fail to correct for correlations when the approximation is not the true posterior. To address this, we construct a new natural gradient called the Variational Predictive Natural Gradient (VPNG). Unlike traditional natural gradients for variational inference, this natural gradient accounts for the relationship between model parameters and variational parameters. We demonstrate the insight with a simple example as well as the empirical value on a classification task, a deep generative model of images, and probabilistic matrix factorization for recommendation.
Code (1)
Tasks
General ClassificationVariational InferenceSimilar Papers 제목 키워드 기반
Noisy Natural Gradient as Variational Inference
Variational Bayesian neural nets combine the flexibility of deep learning with Bayesian uncertainty estimation. Unfortunately, there is a tradeoff between cheap but simple variational families (e.g.~fully factorized) or …
Active LearningEfficient ExplorationReinforcement LearningReinforcement Learning (RL)+1Predictive coding, precision and natural gradients
There is an increasing convergence between biologically plausible computational models of inference and learning with local update rules and the global gradient-based optimization of neural network models employed in mac…
Variational InferenceBayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent
A crucial task in predictive maintenance is estimating the remaining useful life of physical systems. In the last decade, deep learning has improved considerably upon traditional model-based and statistical approaches in…
Variational InferenceStein Variational Model Predictive Control
Decision making under uncertainty is critical to real-world, autonomous systems. Model Predictive Control (MPC) methods have demonstrated favorable performance in practice, but remain limited when dealing with complex pr…
Bayesian InferenceDecision MakingDecision Making Under Uncertaintymodel+1Bayesian Online Natural Gradient (BONG)
We propose a novel approach to sequential Bayesian inference based on variational Bayes (VB). The key insight is that, in the online setting, we do not need to add the KL term to regularize to the prior (which comes from…
Bayesian InferenceSequential Bayesian Inference