24 citations · 168 across the 34 of their papers we have counts for
Showing 2018 · stat.MLShow all
3 papers · 2 filters
stat.ML2018
Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
Laurence Aitchison
We formulate the problem of neural network optimization as Bayesian filtering, where the observations are the backpropagated gradients. While neural network optimization has previo…
stat.ML2018★ 9 cited
Tensor Monte Carlo: particle methods for the GPU era
Laurence Aitchison
Multi-sample, importance-weighted variational autoencoders (IWAE) give tighter bounds and more accurate uncertainty estimates than variational autoencoders (VAE) trained with a sta…
stat.ML2018★ 2 cited
Discrete flow posteriors for variational inference in discrete dynamical systems
Laurence Aitchison, Vincent Adam, Srinivas C. Turaga
Each training step for a variational autoencoder (VAE) requires us to sample from the approximate posterior, so we usually choose simple (e.g. factorised) approximate posteriors in…