pith. machine review for the scientific record. sign in

arxiv: 1401.4082 · v3 · submitted 2014-01-16 · 📊 stat.ML · cs.AI· cs.LG· stat.CO· stat.ME

Recognition: unknown

Stochastic Backpropagation and Approximate Inference in Deep Generative Models

Authors on Pith no claims yet
classification 📊 stat.ML cs.AIcs.LGstat.COstat.ME
keywords datastochasticalgorithmapproximatedeepgenerativeinferencemodel
0
0 comments X
read the original abstract

We marry ideas from deep neural networks and approximate Bayesian inference to derive a generalised class of deep, directed generative models, endowed with a new algorithm for scalable inference and learning. Our algorithm introduces a recognition model to represent approximate posterior distributions, and that acts as a stochastic encoder of the data. We develop stochastic back-propagation -- rules for back-propagation through stochastic variables -- and use this to develop an algorithm that allows for joint optimisation of the parameters of both the generative and recognition model. We demonstrate on several real-world data sets that the model generates realistic samples, provides accurate imputations of missing data and is a useful tool for high-dimensional data visualisation.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Generative Adversarial Networks

    stat.ML 2014-06 accept novelty 9.0

    A generative model is trained to match a data distribution by competing in a minimax game against a discriminator, reaching an equilibrium where the generator recovers the true distribution and the discriminator outpu...

  2. Categorical Reparameterization with Gumbel-Softmax

    stat.ML 2016-11 unverdicted novelty 8.0

    Gumbel-Softmax provides a continuous relaxation of categorical sampling that anneals to discrete samples for gradient-based optimization.

  3. Density estimation using Real NVP

    cs.LG 2016-05 accept novelty 8.0

    Real NVP uses affine coupling layers to create invertible transformations that support exact density estimation, sampling, and latent inference without approximations.

  4. NICE: Non-linear Independent Components Estimation

    cs.LG 2014-10 accept novelty 8.0

    NICE learns a composition of invertible neural-network layers that transform data into independent latent variables, enabling exact log-likelihood training and sampling for density estimation.

  5. Mastering Atari with Discrete World Models

    cs.LG 2020-10 accept novelty 7.0

    DreamerV2 reaches human-level performance on 55 Atari games by learning behaviors inside a separately trained discrete-latent world model.

  6. Dream to Control: Learning Behaviors by Latent Imagination

    cs.LG 2019-12 accept novelty 7.0

    Dreamer learns to control from images by imagining and optimizing behaviors in a learned latent world model, outperforming prior methods on 20 visual tasks in data efficiency and final performance.

  7. CredibleDFGO: Differentiable Factor Graph Optimization with Credibility Supervision

    eess.SP 2026-05 unverdicted novelty 6.0

    CredibleDFGO adds explicit supervision of covariance credibility to differentiable factor graph optimization for GNSS by using proper scoring rules on the predictive distribution, yielding more trustworthy uncertainti...

  8. GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays

    cs.CV 2026-04 unverdicted novelty 6.0

    GazeVaLM provides 960 gaze recordings from 16 radiologists on 60 chest X-rays (half synthetic) plus LLM predictions for diagnostic accuracy and real-fake detection under matched conditions.

  9. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

    cs.AI 2023-08 unverdicted novelty 6.0

    MetaGPT embeds human SOPs into LLM prompts to create role-specialized agent teams that produce more coherent solutions on collaborative software engineering tasks than prior chat-based multi-agent systems.

  10. Information theoretic underpinning of self-supervised learning by clustering

    cs.LG 2026-05 unverdicted novelty 5.0

    SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.

  11. A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models

    cs.LG 2026-05 unverdicted novelty 4.0

    Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.