paper-with-me

Papers

$\alpha$-VAEs : Optimising variational inference by learning data-dependent divergence skew

2021-06-02 · ICML Workshop INNF 2021 7 · Jacob Deasy, Tom Andrew McIver, Nikola Simidjievski, Pietro Lio

The {\em skew-geometric Jensen-Shannon divergence} $\left(\textrm{JS}^{\textrm{G}_{\alpha}}\right)$ allows for an intuitive interpolation between forward and reverse Kullback-Leibler (KL) divergence based on the skew parameter $\alpha$. While the benefits of the skew in $\textrm{JS}^{\textrm{G}_{\alpha}}$ are clear---balancing forward/reverse KL in a comprehensible manner---the choice of optimal skew remains opaque and requires an expensive grid search. In this paper we introduce $\alpha$-VAEs, which extend the $\textrm{JS}^{\textrm{G}_{\alpha}}$ variational autoencoder by allowing for learnable, and therefore data-dependent, skew. We motivate the use of a parameterised skew in the dual divergence by analysing trends dependent on data complexity in synthetic examples. We also prove and discuss the dependency of the divergence minimum on the input data and encoder parameters, before empirically demonstrating that this dependency does not reduce to either direction of KL divergence for benchmark datasets. Finally, we demonstrate that optimised skew values consistently converge across a range of initial values and provide improved denoising and reconstruction properties. These render $\alpha$-VAEs an efficient and practical modelling choice across a range of tasks, datasets, and domains.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

DenoisingVariational Inference

Similar Papers 제목 키워드 기반

Constraining Variational Inference with Geometric Jensen-Shannon Divergence

2020-06-18 · NeurIPS 2020 12 · Jacob Deasy, Nikola Simidjievski, Pietro Liò

We examine the problem of controlling divergences for latent space regularisation in variational autoencoders. Specifically, when aiming to reconstruct example $x\in\mathbb{R}^{m}$ via latent space $z\in\mathbb{R}^{n}$ (…

Variational Inference

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

Learning variational autoencoders via MCMC speed measures

2023-08-26 · Marcel Hirt, Vasileios Kreouzis, Petros Dellaportas

Variational autoencoders (VAEs) are popular likelihood-based generative models which can be efficiently trained by maximizing an Evidence Lower Bound (ELBO). There has been much progress in improving the expressiveness o…

Preventing Posterior Collapse with delta-VAEs

2019-01-10 · ICLR 2019 5 · Ali Razavi, Aäron van den Oord, Ben Poole, Oriol Vinyals

Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or requires augmenting the objective so it does no…

DecoderImage GenerationRepresentation Learning

Alpha-Divergences in Variational Dropout

2017-11-12 · Bogdan Mazoure, Riashat Islam

We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a g…

Variational Inference