paper-with-me

Papers

Conditional Inference in Pre-trained Variational Autoencoders via Cross-coding

2018-05-20 · ICLR 2019 5 · Ga Wu, Justin Domke, Scott Sanner

Variational Autoencoders (VAEs) are a popular generative model, but one in which conditional inference can be challenging. If the decomposition into query and evidence variables is fixed, conditional VAEs provide an attractive solution. To support arbitrary queries, one is generally reduced to Markov Chain Monte Carlo sampling methods that can suffer from long mixing times. In this paper, we propose an idea we term cross-coding to approximate the distribution over the latent variables after conditioning on an evidence assignment to some subset of the variables. This allows generating query samples without retraining the full VAE. We experimentally evaluate three variations of cross-coding showing that (i) they can be quickly optimized for different decompositions of evidence and query and (ii) they quantitatively and qualitatively outperform Hamiltonian Monte Carlo.

📄 PDF Abstract BibTeX arXiv:1805.07785

Code (1)

wuga214/XCoder_VAE_Conditional_Inference 공식 구현 tf

Methods 이 논문이 사용한 방법론

USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Bridging the inference gap in Mutimodal Variational Autoencoders

2025-02-06 · Agathe Senellart, Stéphanie Allassonnière

From medical diagnosis to autonomous vehicles, critical applications rely on the integration of multiple heterogeneous data modalities. Multimodal Variational Autoencoders offer versatile and scalable methods for generat…

Autonomous VehiclesMedical DiagnosisVariational Inference

Learning Conditional Variational Autoencoders with Missing Covariates

2022-03-02 · Siddharth Ramchandran, Gleb Tikhonov, Otto Lönnroth, Pekka Tiikkainen 외

Conditional variational autoencoders (CVAEs) are versatile deep generative models that extend the standard VAE framework by conditioning the generative model with auxiliary covariates. The original CVAE model assumes tha…

Missing ValuesVariational Inference

Hierarchical Bayes Autoencoders

2019-09-25 · Shuangfei Zhai, Carlos Guestrin, Joshua M. Susskind

Autoencoders are powerful generative models for complex data, such as images. However, standard models like the variational autoencoder (VAE) typically have unimodal Gaussian decoders, which cannot effectively represent …

DecoderVariational Inference

Anomaly Detection With Conditional Variational Autoencoders

2020-10-12 · Adrian Alan Pol, Victor Berger, Gianluca Cerminara, Cecile Germain 외

Exploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question. Previous works argued tha…

Anomaly Detection

Deep Variational Inference Without Pixel-Wise Reconstruction

2016-11-16 · Siddharth Agrawal, Ambedkar Dukkipati

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on ma…

Variational Inference