/Bayesian_neural_network_papers

Papers for Bayesian-NN

Bayesian neural network papers

Orginal

  1. A Practical Bayesian Framework for Backpropagation Networks

  2. Bayesian learning for neural networks

What I like the most:

  1. Bayesian learning for neural networks

  2. Weight Uncertainty in Neural Networks

  3. Noisy Natural Gradient as Variational Inference

  4. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

  5. VIME: Variational Information Maximizing Exploration

Towards better training algorithms

  1. Keeping Neural Networks Simple by Minimizing the Description Length of the Weights

  2. Practical Variational Inference for Neural Networks

  3. Weight Uncertainty in Neural Networks

  4. Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

  5. Assumed Density Filtering Methods for Learning Bayesian Neural Networks

  6. Dropout Inference in Bayesian Neural Networks with Alpha-divergences

  7. Deep neural networks as Gaussian Processes

  8. Noisy Natural Gradient as Variational Inference

  9. Bayesian Dark Knowledge

  10. Variational Implicit Processes

Towards more expressive posteriors

  1. Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors

  2. Learning Structured Weight Uncertainty in Bayesian Neural Networks

  3. Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

  4. Kernel Implicit Variational Inference

  5. Bayesian Hypernetworks

  6. Noisy Natural Gradient as Variational Inference

  7. Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam

  8. Adversarial Distillation of Bayesian Neural Network Posteriors

  9. SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradient

Towards better models (Structure + Prior)

  1. Variational Dropout and the Local Reparameterization Trick

  2. Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables

  3. Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

  4. Variational Dropout Sparsifies Deep Neural Networks

  5. Bayesian Compression for Deep Learning

  6. Variance Networks: When Expectation Does Not Meet Your Expectations

  7. Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors

  8. Bayesian Convolutional Neural Networks

  9. Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors

  10. The Description Length of Deep Learning Models

  11. Fixing Variational Bayes: Deterministic Variational Inference for Bayesian Neural Networks

Connecting Bayesian neural networks with Gaussian Processes

  1. Bayesian learning for neural networks

  2. Gaussian process behaviour in wide deep neural networks

  3. Practical Learning of Deep Gaussian Processes via Random Fourier Features

  4. Deep neural networks as Gaussian Processes

  5. Variational Implicit Processes

  6. Mapping Gaussian Process Priors to Bayesian Neural Networks

Towards applications

  1. VIME: Variational Information Maximizing Exploration

  2. Bayesian Optimization with Robust Bayesian Neural Networks

  3. Bayesian GAN

  4. Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks

  5. Model Selection in Bayesian Neural Networks via Horseshoe Priors

  6. Learning Structural Weight Uncertainty for Sequential Decision-Making

  7. Bayesian Gradient Descent: Online Variational Bayes Learning with Increased Robustness to Catastrophic Forgetting and Weight Pruning

  8. Variational Continual Learning

  9. A scalable laplace approximation for neural networks

  10. Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting

  11. Loss-Calibrated Approximate Inference in Bayesian Neural Networks