evidence lower bound
PulseAugur coverage of evidence lower bound — every cluster mentioning evidence lower bound across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Student's t-distribution outperforms Gaussian in Bayesian Neural Networks
Researchers have explored the impact of different likelihood distributions on the performance of Bayesian Neural Networks (BNNs). While Gaussian distributions are commonly used for modeling uncertainty in BNNs due to co…
-
New method advances neural set function learning, reducing computational overhead
Researchers have developed a new method to improve the learning of neural set functions, which are crucial for applications like drug discovery and product recommendation. The approach reinterprets the evidence lower bo…
-
New framework enhances factor analysis with Bayesian variable selection
Researchers have developed a new framework for assessing and selecting the number of factors in partially exploratory factor analysis (PEFA) using variational Bayesian variable selection. This method, termed PCFA VA, em…
-
New SCROLL method optimizes Bayesian neural networks via Bethe free energy
Researchers have developed a new method for training Bayesian neural networks called SCROLL (Shared-Cavity fRee-rOuting Last-Layer). This approach optimizes the Bethe free energy rather than the typical evidence lower b…
-
New method ELBO-T2IAlign calibrates text-image alignment in diffusion models
Researchers have introduced ELBO-T2IAlign, a novel method designed to improve the pixel-level text-image alignment in diffusion models. This technique addresses the issue of misalignment that occurs in diffusion models,…
-
New tools analyze local mass behavior in Bayesian inference
This paper introduces new mathematical tools, the Mass Index and regularised extended KL (RE-KL), to analyze the local-mass behavior in Bayesian inference. These tools go beyond traditional global objectives like KL div…
-
New research enhances diffusion models for robust RL and safe planning
Researchers are developing new methods to improve the robustness and safety of diffusion models in reinforcement learning and planning tasks. One approach, Robust Regularized Policy Iteration (RRPI), addresses transitio…
-
Bayesian model selection via ELBO can overfit, cautioning practitioners
A new paper explores the relationship between the Evidence Lower Bound (ELBO) and Occam's Razor in Bayesian model selection. The research demonstrates that ELBO-based hyperparameter learning can lead to overfitting, con…
-
V-GRPO method enhances denoising generative models with faster, stable reinforcement learning
Researchers have introduced V-GRPO, a novel online reinforcement learning method designed to align denoising generative models with desired outcomes. This approach overcomes previous limitations by efficiently utilizing…