paper-with-me

Papers

Auxiliary Guided Autoregressive Variational Autoencoders

2017-11-30 · ICLR 2018 1 · Thomas Lucas, Jakob Verbeek

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local image statistics respectively, suggest hybrid models that encode global image structure into latent variables while autoregressively modeling low level detail. Previous approaches to such hybrid models restrict the capacity of the autoregressive decoder to prevent degenerate models that ignore the latent variables and only rely on autoregressive modeling. Our contribution is a training procedure relying on an auxiliary loss function that controls which information is captured by the latent variables and what is left to the autoregressive decoder. Our approach can leverage arbitrarily powerful autoregressive decoders, achieves state-of-the art quantitative performance among models with latent variables, and generates qualitatively convincing samples.

📄 PDF Abstract BibTeX arXiv:1711.11479

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder

Similar Papers 제목 키워드 기반

Dueling Decoders: Regularizing Variational Autoencoder Latent Spaces

2019-05-17 · Bryan Seybold, Emily Fertig, Alex Alemi, Ian Fischer

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregre…

Decoder

Dynamic Variational Autoencoders for Visual Process Modeling

2018-03-20 · Alexander Sagel, Hao Shen

This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combini…

Asymmetric Variational Autoencoders

2017-11-20 · Guoqing Zheng, Yiming Yang, Jaime Carbonell

Variational inference for latent variable models is prevalent in various machine learning problems, typically solved by maximizing the Evidence Lower Bound (ELBO) of the true data likelihood with respect to a variational…

Density EstimationVariational Inference

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

2017-01-17 · ICML 2017 8 · Lars Mescheder, Sebastian Nowozin, Andreas Geiger

Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the ex…

Semi-Amortized Variational Autoencoders

2018-02-07 · ICML 2018 7 · Yoon Kim, Sam Wiseman, Andrew C. Miller, David Sontag 외

Amortized variational inference (AVI) replaces instance-specific local inference with a global inference network. While AVI has enabled efficient training of deep generative models such as variational autoencoders (VAE),…

Text GenerationVariational Inference