REVIEW 6 cited by
Reweighted Wake-Sleep
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Reweighted Wake-Sleep
read the original abstract
Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been proposed to train them. The wake-sleep algorithm relies on training not just the directed generative model but also a conditional generative model (the inference network) that runs backward from visible to latent, estimating the posterior distribution of latent given visible. We propose a novel interpretation of the wake-sleep algorithm which suggests that better estimators of the gradient can be obtained by sampling latent variables multiple times from the inference network. This view is based on importance sampling as an estimator of the likelihood, with the approximate inference network as a proposal distribution. This interpretation is confirmed experimentally, showing that better likelihood can be achieved with this reweighted wake-sleep procedure. Based on this interpretation, we propose that a sigmoidal belief network is not sufficiently powerful for the layers of the inference network in order to recover a good estimator of the posterior distribution of latent variables. Our experiments show that using a more powerful layer model, such as NADE, yields substantially better generative models.
Forward citations
Cited by 6 Pith papers
-
GradInf: Gradient Estimation as Probabilistic Inference
Gradient estimation of probabilistic programs reduces soundly to probabilistic inference after programmable coupling and factorization, enabling new low-variance estimators that beat baselines.
-
Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation
Introduces the first amortized neural posterior estimator conditioned on both data and temperature β for generalized Bayesian inference, matching MCMC performance on standard SBI benchmarks.
-
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
A nonequilibrium latent-variable Markov model spontaneously develops cycles during likelihood training that enhance generative performance over equilibrium approaches.
-
LeAct: Learning to Reason from Expert Actions
An AI can learn to reason by sampling explanations for an expert's actions and keeping only the ones that help it predict those actions.
-
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
In an asymmetric visible-hidden Markov-chain generative model, likelihood-type training spontaneously produces nonequilibrium latent cycles, and models with stronger cycles reproduce digit-class frequencies more faithfully.
-
Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space
Proposes Latent Interacting Particle Systems with an efficient parameterization of twist potentials to enable approximate posterior inference for coupled continuous-time hidden Markov models via twisted sequential Mon...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.