Variational Inference
PulseAugur coverage of Variational Inference — every cluster mentioning Variational Inference across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Bayesian Neural Networks leverage symmetry for improved deep learning performance
Researchers have explored the role of symmetries in deep learning, particularly in Bayesian Neural Networks (BNNs). They investigated whether imposing symmetry constraints on network architecture or learning them throug…
-
New AI inference methods tackle high-dimensional variance and posterior collapse
Researchers have introduced Entropic Transport Descent (ETD), a novel particle-based variational inference method that uses entropy-regularized optimal transport to improve approximations of intractable distributions. U…
-
New SN-VI Framework Enhances Latent Variable Modeling in AI
Researchers have developed Structured Nonparametric Variational Inference (SN-VI), a new framework that models complex dependencies among latent variables in posterior approximation using multivariate spline techniques.…
-
New IVRS Method Enhances Bayesian Machine Learning Posterior Approximation
Researchers have introduced Implicit Variational Rejection Sampling (IVRS), a novel method designed to enhance posterior approximation in Bayesian machine learning. This technique combines implicit distributions modeled…
-
New VPR method improves Bayesian posterior sampling accuracy
Researchers have introduced Variational Predictive Resampling (VPR), a new method designed to improve the accuracy of Bayesian posterior sampling. VPR leverages variational inference's predictive capabilities within a r…
-
New neural tilting framework improves AI safety inference
Researchers have developed a new neural exponential tilting framework for variational inference in Lévy-driven stochastic differential equations. This method addresses the intractability of Bayesian inference for proces…
-
New AI research explores advanced methods for uncertainty estimation and Bayesian inference
Researchers have developed a new variational Bayesian framework that directly targets the posterior-predictive distribution, jointly learning approximations for both the posterior and predictive distributions. This appr…
-
New paper derives exponential family results from single KL identity
Researchers have identified a fundamental identity for exponential families, which are distributions crucial to modern machine learning techniques like softmax and Gaussian distributions. This identity simplifies the de…
-
Symmetry Guarantees Statistic Recovery in Variational Inference
Two new papers explore how symmetries in target distributions can guarantee the recovery of certain statistics during variational inference, even when the chosen variational family is misspecified. The research provides…