paper-with-me

Papers

Bidirectional Generative Modeling Using Adversarial Gradient Estimation

2020-02-21 · Xinwei Shen, Tong Zhang, Kani Chen

This paper considers the general $f$-divergence formulation of bidirectional generative modeling, which includes VAE and BiGAN as special cases. We present a new optimization method for this formulation, where the gradient is computed using an adversarially learned discriminator. In our framework, we show that different divergences induce similar algorithms in terms of gradient evaluation, except with different scaling. Therefore this paper gives a general recipe for a class of principled $f$-divergence based generative modeling methods. Theoretical justifications and extensive empirical studies are provided to demonstrate the advantage of our approach over existing methods.

📄 PDF Abstract BibTeX arXiv:2002.09161

Code (2)

xwshen51/AGE 공식 구현 pytorch
xwshen51/AGES 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

BiGAN A BiGAN, or Bidirectional GAN, is a type of generative adversarial network where the generator not only maps latent samples to generated data, but also has an inverse…
USD Coin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Bounds all around: training energy-based models with bidirectional bounds

2021-11-01 · NeurIPS 2021 12 · Cong Geng, Jia Wang, Zhiyong Gao, Jes Frellsen 외

Energy-based models (EBMs) provide an elegant framework for density estimation, but they are notoriously difficult to train. Recent work has established links to generative adversarial networks, where the EBM is trained …

AllDensity Estimation

Sounderfeit: Cloning a Physical Model with Conditional Adversarial Autoencoders

2018-02-22 · Stephen Sinclair

An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture var…

parameter estimationResynthesis

Sounderfeit: Cloning a Physical Model using a Conditional Adversarial Autoencoder

2018-06-25 · Stephen Sinclair

An adversarial autoencoder conditioned on known parameters of a physical modeling bowed string synthesizer is evaluated for use in parameter estimation and resynthesis tasks. Latent dimensions are provided to capture var…

parameter estimationResynthesis

Exploring bidirectional bounds for minimax-training of Energy-based models

2025-06-05 · Cong Geng, Jia Wang, Li Chen, Zhiyong Gao 외

Energy-based models (EBMs) estimate unnormalized densities in an elegant framework, but they are generally difficult to train. Recent work has linked EBMs to generative adversarial networks, by noting that they can be tr…

Density Estimation

Discovering state-parameter mappings in subsurface models using generative adversarial networks

2018-10-30 · Alexander Y. Sun

A fundamental problem in geophysical modeling is related to the identification and approximation of causal structures among physical processes. However, resolving the bidirectional mappings between physical parameters an…

Translation