Search Results for author:
Found 10 papers, 4 papers with code
Marginal Likelihoods from Monte Carlo Markov Chains
In this paper, we present a method for computing the marginal likelihood, also known as the model likelihood or Bayesian evidence, from Markov Chain Monte Carlo (MCMC), or other sampled posterior distributions.
Computation Cosmology and Nongalactic Astrophysics
Learning Dynamics of Linear Denoising Autoencoders
Here we develop theory for how noise influences learning in DAEs.
Critical initialisation for deep signal propagation in noisy rectifier neural networks
Simulations and experiments on real-world data confirm that our proposed initialisation is able to stably propagate signals in deep networks, while using an initialisation disregarding noise fails to do so.
On the expected behaviour of noise regularised deep neural networks as Gaussian processes
Recent work has established the equivalence between deep neural networks and Gaussian processes (GPs), resulting in so-called neural network Gaussian processes (NNGPs).
If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks
Our results therefore suggest that, in the shallow-to-moderate depth setting, critical initialisation provides zero performance gains when compared to off-critical initialisations and that searching for off-critical initialisations that might improve training speed or generalisation, is likely to be a fruitless endeavour.
Stabilising priors for robust Bayesian deep learning
Bayesian neural networks (BNNs) have developed into useful tools for probabilistic modelling due to recent advances in variational inference enabling large scale BNNs.
Stochastic Gradient Annealed Importance Sampling for Efficient Online Marginal Likelihood Estimation
An important benefit of our approach is that the marginal likelihood is calculated in an online fashion as data becomes available, allowing the estimates to be used for applications such as online weighted model combination.
Performance-Agnostic Fusion of Probabilistic Classifier Outputs
The intuition behind this approach is that classifiers trained for the same task should typically exhibit regularities in their outputs on a new task; the predictions of classifiers which differ significantly from those of others are thus given less credence using our approach.
SIReN-VAE: Leveraging Flows and Amortized Inference for Bayesian Networks
Subsequent work has explored incorporating more complex distributions and dependency structures: including normalizing flows in the encoder network allows latent variables to entangle non-linearly, creating a richer class of distributions for the approximate posterior, and stacking layers of latent variables allows more complex priors to be specified for the generative model.
Graphical Residual Flows
Furthermore, our model provides performance competitive with other graphical flows for both density estimation and inference tasks.
