paper-with-me

Papers

Learning in Variational Autoencoders with Kullback-Leibler and Renyi Integral Bounds

2018-07-05 · Septimia Sârbu, Riccardo Volpi, Alexandra Peşte, Luigi Malagò

In this paper we propose two novel bounds for the log-likelihood based on Kullback-Leibler and the R\'{e}nyi divergences, which can be used for variational inference and in particular for the training of Variational AutoEncoders. Our proposal is motivated by the difficulties encountered in training VAEs on continuous datasets with high contrast images, such as those with handwritten digits and characters, where numerical issues often appear unless noise is added, either to the dataset during training or to the generative model given by the decoder. The new bounds we propose, which are obtained from the maximization of the likelihood of an interval for the observations, allow numerically stable training procedures without the necessity of adding any extra source of noise to the data.

📄 PDF Abstract BibTeX arXiv:1807.01889

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderVariational Inference

Similar Papers 제목 키워드 기반

Tutorial: Deriving the Standard Variational Autoencoder (VAE) Loss Function

2019-07-21 · Stephen Odaibo

In Bayesian machine learning, the posterior distribution is typically computationally intractable, hence variational inference is often required. In this approach, an evidence lower bound on the log likelihood of data is…

Variational Inference

On the Importance of the Kullback-Leibler Divergence Term in Variational Autoencoders for Text Generation

2019-09-30 · WS 2019 11 · Victor Prokhorov, Ehsan Shareghi, Yingzhen Li, Mohammad Taher Pilehvar 외

Variational Autoencoders (VAEs) are known to suffer from learning uninformative latent representation of the input due to issues such as approximated posterior collapse, or entanglement of the latent space. We impose an …

Text Generation

Balancing reconstruction error and Kullback-Leibler divergence in Variational Autoencoders

2020-02-18 · Andrea Asperti, Matteo Trentin

In the loss function of Variational Autoencoders there is a well known tension between two components: the reconstruction loss, improving the quality of the resulting images, and the Kullback-Leibler divergence, acting a…

Mixture weights optimisation for Alpha-Divergence Variational Inference

2021-06-09 · NeurIPS 2021 12 · Kamélia Daudel, Randal Douc

This paper focuses on $\alpha$-divergence minimisation methods for Variational Inference. More precisely, we are interested in algorithms optimising the mixture weights of any given mixture model, without any information…

Variational Inference

Mutual Information Constraints for Monte-Carlo Objectives

2020-12-01 · Gábor Melis, András György, Phil Blunsom

A common failure mode of density models trained as variational autoencoders is to model the data without relying on their latent variables, rendering these variables useless. Two contributing factors, the underspecificat…