Incorporating Bayesian approaches in Deep Learning Research
The blog will take the form of a survey paper as we summarize the proceedings from the Symposium on Approximate Bayesian Inference, during NeurIPS, 2019 in Vancouver. Rightly so, I focused on the Bayesian workshop as it emphasized the fundamentals, rather than bleeding-edge results. The knowledge that can lead to progress results from understanding how things work on a foundational level.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian InferenceDeep LearningSurveySimilar Papers 제목 키워드 기반
Enhanced Input Modeling for Construction Simulation using Bayesian Deep Neural Networks
This paper aims to propose a novel deep learning-integrated framework for deriving reliable simulation input models through incorporating multi-source information. The framework sources and extracts multisource data gene…
Decision MakingBayesian Optimization with Shape Constraints
In typical applications of Bayesian optimization, minimal assumptions are made about the objective function being optimized. This is true even when researchers have prior information about the shape of the function with …
Bayesian OptimizationBIG-bench Machine LearningData augmentation in Bayesian neural networks and the cold posterior effect
Bayesian neural networks that incorporate data augmentation implicitly use a ``randomly perturbed log-likelihood [which] does not have a clean interpretation as a valid likelihood function'' (Izmailov et al. 2021). Here,…
Bayesian InferenceData AugmentationvalidIs Sequence Information All You Need for Bayesian Optimization of Antibodies?
Bayesian optimization is a natural candidate for the engineering of antibody therapeutic properties, which is often iterative and expensive. However, finding the optimal choice of surrogate model for optimization over th…
Protein Language ModelIncorporating Expert Knowledge into Bayesian Causal Discovery of Mixtures of Directed Acyclic Graphs
Bayesian causal discovery benefits from prior information elicited from domain experts, and in heterogeneous domains any prior knowledge would be badly needed. However, so far prior elicitation approaches have assumed a …