No article text was recorded for this version.
weight-space prior limitations
Version 2 of 266 papers78 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Functional Priors for Bayesian Neural Networks through Wasserstein Distance Minimization to Gaussian Processes
- Blog: How Good is the Bayes Posterior in Deep Neural Networks Really?
- Blog: Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
- Blog: Disentangling the Roles of Curation, Data-Augmentation and the Prior in the Cold Posterior Effect
- Blog: Priors in Bayesian Deep Learning: A Review
- Blog: Bayesian Neural Networks with Domain Knowledge Priors
- Blog: All You Need is a Good Functional Prior for Bayesian Deep Learning
- Blog: Liberty or Depth: Deep Bayesian Neural Nets Do Not Need Complex Weight Posterior Approximations
- Blog: Imposing Functional Priors on Bayesian Neural Networks
- Blog: Functional Stochastic Gradient MCMC for Bayesian Neural Networks
- Blog: A Primer on Bayesian Neural Networks: Review and Debates
- Blog: Try Depth Instead of Weight Correlations: Mean-field is a Less Restrictive Assumption for Deeper Networks
- Blog: Bayesian Numerical Integration with Neural Networks
- Blog: Noise Contrastive Priors for Functional Uncertainty
- Blog: Gaussian Processes for Regression
- Blog: Tractable Function-Space Variational Inference in Bayesian Neural Networks
- Blog: On the Interplay of Priors and Overparametrization in Bayesian Neural Network Posteriors
- Blog: Reliable Uncertainty Estimates in Deep Neural Networks using Noise Contrastive Priors
- Blog: Functional Stochastic Gradient MCMC for Bayesian Neural Networks
- Blog: Function-space Inference with Sparse Implicit Processes
- Blog: Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data
- Blog: Penalising the biases in norm regularisation enforces sparsity
- Blog: FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
- Blog: Learning Priors for Invariance
- Blog: Functional variational Bayesian Neural Networks
- Blog: Exact marginal prior distributions of finite Bayesian neural networks
- Blog: Function-Space Regularization for Deep Bayesian Classification
- Blog: Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
- Blog: Bayesian Backpropagation Over I-O Functions Rather Than Weights
- Blog: Exact priors of finite neural networks
- Blog: FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
- Blog: Wide Bayesian neural networks have a simple weight posterior: theory and accelerated sampling
- Blog: Baysian numerical integration with neural networks
- Blog: Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
- Blog: Incorporating Interpretable Output Constraints in Bayesian Neural Networks
- Blog: Noise Contrastive Priors for Functional Uncertainty
- Blog: PoRB-Nets: Poisson Process Radial Basis Function Networks
- Blog: Observation Noise and Initialization in Wide Neural Networks
- Blog: High-Fidelity Transfer of Functional Priors for Wide Bayesian Neural Networks by Learning Activations
- Blog: GPan-LoRA: Gaussian Process Amortized Networks for Bayesian Low-Rank Adaptation in Large Language Models
- Blog: How do infinite width bounded norm networks look in function space?
- Blog: Predictive Complexity Priors
- Blog: The Case for Bayesian Deep Learning
- Blog: Functional Variational Inference based on Stochastic Process Generators
- Blog: Amortising Inference and Meta-Learning Priors in Neural Networks
- Blog: Generalized Variational Inference in Function Spaces: Gaussian Measures meet Bayesian Deep Learning
- Blog: Function-space Inference with Sparse Implicit Processes
- Blog: Incorporating functional summary information in Bayesian neural networks using a Dirichlet process likelihood approach
- Blog: Function-space Parameterization of Neural Networks for Sequential Learning
- Blog: Model Selection for Bayesian Autoencoders
- Blog: Precise characterization of the prior predictive distribution of deep ReLU networks
- Blog: On the Expressiveness of Approximate Inference in Bayesian Neural Networks
- Blog: Regularized KL-Divergence for Well-Defined Function-Space Variational Inference in Bayesian neural networks
- Blog: The Ridgelet Prior: A Covariance Function Approach to Prior Specification for Bayesian Neural Networks
- Blog: Function Space Particle Optimization for Bayesian Neural Networks
- Blog: On Equivalences between Weight and Function-Space Langevin Dynamics
- Blog: Drug Discovery under Covariate Shift with Domain-Informed Prior Distributions over Functions
- Blog: Low-Budget Simulation-Based Inference with Bayesian Neural Networks
- Blog: The Functional Neural Process
- Blog: Pathologies in priors and inference for Bayesian transformers
Showing 60 of 66 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_weight_space_prior_limitations_bd7301d4,
title = {weight-space prior limitations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/weight-space-prior-limitations/rdr_bd7301d45fc44e05a9acda5094306ada},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_weight_space_prior_limitations_bd7301d4_v2,
title = {weight-space prior limitations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/weight-space-prior-limitations/rdr_bd7301d45fc44e05a9acda5094306ada/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}