Results 261 to 270 of about 5,051,769 (292)
Stochastic variational inference
J. Mach. Learn. Res., 2012 We develop stochastic variational inference, a scalable algorithm for approximating posterior distributions. We develop this technique for a large class of probabilistic models and we demonstrate it with two probabilistic topic models, latent Dirichlet ...
M. Hoffman +3 more
semanticscholar +5 more sources
Some of the next articles are maybe not open access.
Related searches:
Related searches:
Continual Learning via Sequential Function-Space Variational Inference
International Conference on Machine Learning, 2023Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice.
Tim G. J. Rudner +4 more
semanticscholar +1 more source
Tractable Function-Space Variational Inference in Bayesian Neural Networks
Neural Information Processing Systems, 2023Reliable predictive uncertainty estimation plays an important role in enabling the deployment of neural networks to safety-critical settings. A popular approach for estimating the predictive uncertainty of neural networks is to define a prior ...
Tim G. J. Rudner +3 more
semanticscholar +1 more source
On the Convergence of Black-Box Variational Inference
Neural Information Processing Systems, 2023We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference. While preliminary investigations worked on simplified versions of BBVI (e.g., bounded domain, bounded support ...
Kyurae Kim +4 more
semanticscholar +1 more source
Representation Uncertainty in Self-Supervised Learning as Variational Inference
IEEE International Conference on Computer Vision, 2022In this study, a novel self-supervised earning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties.
Hiroki Nakamura +2 more
semanticscholar +1 more source
Proceedings of the 26th Annual International Conference on Machine Learning, 2009
We propose a deterministic method to evaluate the integral of a positive function based on soft-binning functions that smoothly cut the integral into smaller integrals that are easier to approximate. In combination with mean-field approximations for each individual sub-part this leads to a tractable algorithm that alternates between the optimization of
Guillaume Bouchard, Onno Zoeter
openaire +1 more source
We propose a deterministic method to evaluate the integral of a positive function based on soft-binning functions that smoothly cut the integral into smaller integrals that are easier to approximate. In combination with mean-field approximations for each individual sub-part this leads to a tractable algorithm that alternates between the optimization of
Guillaume Bouchard, Onno Zoeter
openaire +1 more source
VarGrad: A Low-Variance Gradient Estimator for Variational Inference
Neural Information Processing Systems, 2020We analyse the properties of an unbiased gradient estimator of the ELBO for variational inference, based on the score function method with leave-one-out control variates.
Lorenz Richter +4 more
semanticscholar +1 more source
Metric Gaussian variational inference
2020One main result of this dissertation is the development of Metric Gaussian Variational Inference (MGVI), a method to perform approximate inference in extremely high dimensions and for complex probabilistic models. The problem with high-dimensional and complex models is twofold. Fist, to capture the true posterior distribution accurately, a sufficiently
openaire +3 more sources
Inferences on the common coefficient of variation
Statistics in Medicine, 2005The coefficient of variation is often used as a measure of precision and reproducibility of data in medical and biological science. This paper considers the problem of making inference about the common population coefficient of variation when it is a priori suspected that several independent samples are from populations with a common coefficient of ...
openaire +2 more sources