paper-with-me

Papers

Geometry-Aware Hamiltonian Variational Auto-Encoder

2020-10-22 · Clément Chadebec, Clément Mantoux, Stéphanie Allassonnière

Variational auto-encoders (VAEs) have proven to be a well suited tool for performing dimensionality reduction by extracting latent variables lying in a potentially much smaller dimensional space than the data. Their ability to capture meaningful information from the data can be easily apprehended when considering their capability to generate new realistic samples or perform potentially meaningful interpolations in a much smaller space. However, such generative models may perform poorly when trained on small data sets which are abundant in many real-life fields such as medicine. This may, among others, come from the lack of structure of the latent space, the geometry of which is often under-considered. We thus propose in this paper to see the latent space as a Riemannian manifold endowed with a parametrized metric learned at the same time as the encoder and decoder networks. This metric is then used in what we called the Riemannian Hamiltonian VAE which extends the Hamiltonian VAE introduced by arXiv:1805.11328 to better exploit the underlying geometry of the latent space. We argue that such latent space modelling provides useful information about its underlying structure leading to far more meaningful interpolations, more realistic data-generation and more reliable clustering.

📄 PDF Abstract BibTeX arXiv:2010.11518

Code (1)

clementchadebec/benchmark_VAE pytorch

Tasks

ClusteringDecoderDimensionality Reduction

Methods 이 논문이 사용한 방법론

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

Similar Papers 제목 키워드 기반

Hamiltonian Variational Auto-Encoder

2018-05-29 · NeurIPS 2018 12 · Anthony L. Caterini, Arnaud Doucet, Dino Sejdinovic

Variational Auto-Encoders (VAEs) have become very popular techniques to perform inference and learning in latent variable models as they allow us to leverage the rich representational power of neural networks to obtain f…

Variational Inference

Quasi-symplectic Langevin Variational Autoencoder

2020-09-02 · Zihao Wang, Hervé Delingette

Variational autoencoder (VAE) is a very popular and well-investigated generative model in neural learning research. To leverage VAE in practical tasks dealing with a massive dataset of large dimensions, it is required to…

Variational Inference

Unsupervised Learning of Lagrangian Dynamics from Images for Prediction and Control

2020-07-03 · NeurIPS 2020 12 · Yaofeng Desmond Zhong, Naomi Ehrich Leonard

Recent approaches for modelling dynamics of physical systems with neural networks enforce Lagrangian or Hamiltonian structure to improve prediction and generalization. However, when coordinates are embedded in high-dimen…

Prediction

NeuTra-lizing Bad Geometry in Hamiltonian Monte Carlo Using Neural Transport

2019-03-09 · Matthew Hoffman, Pavel Sountsov, Joshua V. Dillon, Ian Langmore 외

Hamiltonian Monte Carlo is a powerful algorithm for sampling from difficult-to-normalize posterior distributions. However, when the geometry of the posterior is unfavorable, it may take many expensive evaluations of the …

Variational Inference

High-Dimensional Latents Should Be Diagnosed Through Phase Structure

2026-05-23 · Alejandro Ascarate, Leo Lebrat, Rodrigo Santa Cruz, Clinton Fookes 외 arxiv

We study autoencoder and variational-autoencoder latent spaces through the lens of spin-glass theory. The paper has two components. First, we formalize a latent-space spin-glass dictionary: for a fixed decoder, the recon…

Anomaly Detection