Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface
arXiv:2107.06393
Abstract
Modeling complex phenomena typically involves the use of both discrete and continuous variables. Such a setting applies across a wide range of problems, from identifying trends in time-series data to performing effective compositional scene understanding in images. Here, we propose Hybrid Memoised Wake-Sleep (HMWS), an algorithm for effective inference in such hybrid discrete-continuous models. Prior approaches to learning suffer as they need to perform repeated expensive inner-loop discrete inference. We build on a recent approach, Memoised Wake-Sleep (MWS), which alleviates part of the problem by memoising discrete variables, and extend it to allow for a principled and effective way to handle continuous variables by learning a separate recognition model used for importance-sampling based approximate inference and marginalization. We evaluate HMWS in the GP-kernel learning and 3D scene understanding domains, and show that it outperforms current state-of-the-art inference methods.
References in corpus (13)
- Auto-Encoding Variational Bayes
- Categorical Reparameterization with Gumbel-Softmax
- Variational Inference with Normalizing Flows
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Structure Discovery in Nonparametric Regression through Compositional Kernel Search
- Neural Variational Inference and Learning in Belief Networks
- Gradient Estimation Using Stochastic Computation Graphs
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models
- Variational inference for Monte Carlo objectives
- Accelerating 3D Deep Learning with PyTorch3D
- Computer-Aided Design as Language
- HOUDINI: Lifelong Learning as Program Synthesis
- Revisiting Reweighted Wake-Sleep for Models with Stochastic Control Flow