SOTAVerified

Bayesian Inference

Bayesian Inference is a methodology that employs Bayes Rule to estimate parameters (and their full posterior).

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 211–220 of 2226 papers

TitleStatusHype
Variational Dropout and the Local Reparameterization TrickCode1
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep LearningCode1
Weight Uncertainty in Neural NetworksCode1
SAME but Different: Fast and High-Quality Gibbs Parameter EstimationCode1
Semi-Supervised Learning with Deep Generative ModelsCode1
Bayesian inference for logistic models using Polya-Gamma latent variablesCode1
A Simple Approximate Bayesian Inference Neural Surrogate for Stochastic Petri Net ModelsCode0
The Bayesian Approach to Continual Learning: An Overview—0
Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning—0
Scalable Bayesian Low-Rank Adaptation of Large Language Models via Stochastic Variational Subspace InferenceCode0
Show:102550
← PrevPage 22 of 223Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1F-SWAAccuracy83.61—Unverified
2F-SWAGAccuracy80.93—Unverified