simplyblockJun 28, 2024

How #MachineLearning and #ProbabilisticModel can help with automatically optimizing the performance of systems like databases.

In this week's episode of Cloud Commute podcast, our host @noctarius2k talks to Luigi Nardi from #DBtune about usages of #ArtificialIntelligence to understand system performance and recommend configuration changes to adjust them for highest performance automatically.

Find the full episode at our show page for the necessary links https://simplyblock.io/cloud-commute-podcast

Cloud Commute | simplyblock.io

Cloud Commute is your weekly 20 minute podcast, talking with guests about all things cloud, storage, security, Kubernetes, and others.

simplyblock.io
Dominic BoutetDec 20, 2022

#arxivfeed :

"Auto-Encoding Variational Bayes"
https://arxiv.org/abs/1312.6114

#MachineLearning #VariationalBayes #Bayesian #Inference #ProbabilisticModel #AutoEncoder #DeepLearning

Auto-Encoding Variational Bayes

How can we perform efficient inference and learning in directed probabilistic models, in the presence of continuous latent variables with intractable posterior distributions, and large datasets? We introduce a stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case. Our contributions are two-fold. First, we show that a reparameterization of the variational lower bound yields a lower bound estimator that can be straightforwardly optimized using standard stochastic gradient methods. Second, we show that for i.i.d. datasets with continuous latent variables per datapoint, posterior inference can be made especially efficient by fitting an approximate inference model (also called a recognition model) to the intractable posterior using the proposed lower bound estimator. Theoretical advantages are reflected in experimental results.

arXiv.org