High-Order Stochastic Gradient Thermostats for Bayesian Learning of Deep Models
arXiv:1512.07662
Abstract
Learning in deep models using Bayesian methods has generated significant attention recently. This is largely because of the feasibility of modern Bayesian methods to yield scalable learning and inference, while maintaining a measure of uncertainty in the model parameters. Stochastic gradient MCMC algorithms (SG-MCMC) are a family of diffusion-based sampling methods for large-scale Bayesian learning. In SG-MCMC, multivariate stochastic gradient thermostats (mSGNHT) augment each parameter of interest, with a momentum and a thermostat variable to maintain stationary distributions as target posterior distributions. As the number of variables in a continuous-time diffusion increases, its numerical approximation error becomes a practical bottleneck, so better use of a numerical integrator is desirable. To this end, we propose use of an efficient symmetric splitting integrator in mSGNHT, instead of the traditional Euler integrator. We demonstrate that the proposed scheme is more accurate, robust, and converges faster. These properties are demonstrated to be desirable in Bayesian deep learning. Extensive experiments on two canonical models and their deep extensions demonstrate that the proposed scheme improves general Bayesian posterior sampling, particularly for deep models.
arXiv commentAAAI 2016
References in corpus (12)
- Auto-Encoding Variational Bayes
- Weight Uncertainty in Neural Networks
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
- Stochastic Gradient Hamiltonian Monte Carlo
- Bayesian Dark Knowledge
- A Complete Recipe for Stochastic Gradient MCMC
- Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networks
- On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators
- Deep Temporal Sigmoid Belief Networks for Sequence Modeling
- Bayesian Conditional Density Filtering
- A Generative Model for Deep Convolutional Learning