Parsimonious Bayesian deep networks

Mingyuan Zhou

Abstract

Combining Bayesian nonparametrics and a forward model selection strategy, we construct parsimonious Bayesian deep networks (PBDNs) that infer capacity-regularized network architectures from the data and require neither cross-validation nor fine-tuning when training the model. One of the two essential components of a PBDN is the development of a special infinite-wide single-hidden-layer neural network, whose number of active hidden units can be inferred from the data. The other one is the construction of a greedy layer-wise learning algorithm that uses a forward model selection criterion to determine when to stop adding another hidden layer. We develop both Gibbs sampling and stochastic gradient descent based maximum a posteriori inference for PBDNs, providing state-of-the-art classification accuracy and interpretable data subtypes near the decision boundaries, while maintaining low computational complexity for out-of-sample prediction.
BibTeX
@inproceedings{zhou2018parsimonious,
  author = {Mingyuan Zhou},
  title = {{Parsimonious Bayesian deep networks}},
  booktitle = {Advances in Neural Information Processing Systems},
  year = {2018},
  url = {https://openreview.net/forum?id=rkZjjD-_bH},
}

Loading related content...

Figure