Controllable generation is one of the key requirements for successful adoptionof deep generative models in real-world applications, but it still remains as a greatchallenge.

Neural network quantization is one of the most effective ways to improve the efficiency of neural networks. Quantization allows weights and activations to be represented in low bit-width formats, e.g. 8 bit integers (INT8).

However, it is unclear how to best fit low-rank RNNs to data consisting of noisy observations of an underlying stochastic system. Here, we propose to fit stochastic low-rank RNNs with variational sequential Monte Carlo methods.

Foraquickcomparison, see Table1and Related Work. Asreinforcement grows, t representation Q-function, RLalgorithms.

Our approach requires no additional training and enables highly flexible module composition.

Hierarchical Bayesian methods enable information sharing across regression problems on multiple groups of data.