Filtering Variational Objectives
arXiv:1705.09279
Abstract
When used as a surrogate objective for maximum likelihood estimation in latent variable models, the evidence lower bound (ELBO) produces state-of-the-art results. Inspired by this, we consider the extension of the ELBO to a family of lower bounds defined by a particle filter's estimator of the marginal likelihood, the filtering variational objectives (FIVOs). FIVOs take the same arguments as the ELBO, but can exploit a model's sequential structure to form tighter bounds. We present results that relate the tightness of FIVO's bound to the variance of the particle filter's estimator by considering the generic case of bounds defined as log-transformed likelihood estimators. Experimentally, we show that training with FIVO results in substantial improvements over training the same model architecture with the ELBO on sequential data.
References in corpus (23)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- WaveNet: A Generative Model for Raw Audio
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Pixel Recurrent Neural Networks
- Density estimation using Real NVP
- f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
- Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Automatic Differentiation Variational Inference
- Learning in Implicit Generative Models
- Sequential Neural Models with Stochastic Layers
- Generalized Multiple Importance Sampling
- Variational inference for Monte Carlo objectives
- Hierarchical Implicit Models and Likelihood-Free Variational Inference
- A Deep and Tractable Density Estimator
- Auto-Encoding Sequential Monte Carlo
- Computing Upper and Lower Bounds on Likelihoods in Intractable Networks
- Inference Networks for Sequential Monte Carlo in Graphical Models
- Variational Sequential Monte Carlo
- Neural Adaptive Sequential Monte Carlo
- Comparison of Maximum Likelihood and GAN-based training of Real NVPs
- Sandwiching the marginal likelihood using bidirectional Monte Carlo
- Reweighted Wake-Sleep