中文
相关论文

相关论文: Entropy-Based Characterisation of the Polarised Re…

200 篇论文

Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one…

机器学习 · 计算机科学 2019-03-20 Shuyu Lin , Ronald Clark , Robert Birke , Niki Trigoni , Stephen Roberts

The variational autoencoder (VAE) is a powerful generative model that can estimate the probability of a data point by using latent variables. In the VAE, the posterior of the latent variable given the data point is regularized by the prior…

机器学习 · 统计学 2019-12-30 Hiroshi Takahashi , Tomoharu Iwata , Yuki Yamanaka , Masanori Yamada , Satoshi Yagi

Variational autoencoders (VAEs) are one of the powerful unsupervised learning frameworks in NLP for latent representation learning and latent-directed generation. The classic optimization goal of VAEs is to maximize the Evidence Lower Bound…

机器学习 · 计算机科学 2022-11-02 Jianfei Zhang , Jun Bai , Chenghua Lin , Yanmeng Wang , Wenge Rong

Variational Autoencoder is a scalable method for learning latent variable models of complex data. It employs a clear objective that can be easily optimized. However, it does not explicitly measure the quality of learned representations. We…

机器学习 · 计算机科学 2020-05-29 Andriy Serdega , Dae-Shik Kim

Variational autoencoders (VAEs) are a popular generative model used to approximate distributions. The encoder part of the VAE is used in amortized learning of latent variables, producing a latent representation for data samples. Recently,…

机器学习 · 统计学 2023-05-12 Daniel G. Edelberg , Roy R. Lederman

Variational autoencoders (VAEs) face a notorious problem wherein the variational posterior often aligns closely with the prior, a phenomenon known as posterior collapse, which hinders the quality of representation learning. To mitigate this…

机器学习 · 统计学 2023-10-25 Yuma Ichikawa , Koji Hukushima

Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which individual features are most salient. While recent work from our group and…

Variational Autoencoders (VAEs) have become a popular approach for dimensionality reduction. However, despite their ability to identify latent low-dimensional structures embedded within high-dimensional data, these latent representations…

机器学习 · 统计学 2020-08-27 Kaspar Märtens , Christopher Yau

This work presents an analysis of the hidden representations of Variational Autoencoders (VAEs) using the Intrinsic Dimension (ID) and the Information Imbalance (II). We show that VAEs undergo a transition in behaviour once the bottleneck…

机器学习 · 计算机科学 2024-11-05 Charles Camboulin , Diego Doimo , Aldo Glielmo

Variational Autoencoders (VAE) are widely used for dimensionality reduction of large-scale tabular and image datasets, under the assumption of independence between data observations. In practice, however, datasets are often correlated, with…

机器学习 · 统计学 2024-12-25 Giora Simchoni , Saharon Rosset

We present a deep-learning Variational Encoder-Decoder (VED) framework for learning data-driven low-dimensional representations of the relationship between high-dimensional parameters of a physical system and the system's high-dimensional…

机器学习 · 计算机科学 2024-12-09 Subashree Venkatasubramanian , David A. Barajas-Solano

Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…

机器学习 · 统计学 2019-09-12 Jan Stühmer , Richard E. Turner , Sebastian Nowozin

Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation. One key factor is the exploitation of smooth latent structures to guide the generation. However, the…

机器学习 · 计算机科学 2019-12-02 Le Fang , Chunyuan Li , Jianfeng Gao , Wen Dong , Changyou Chen

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

机器学习 · 计算机科学 2019-10-08 Bin Dai , Yu Wang , John Aston , Gang Hua , David Wipf

In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating factors are also statistically independent, disentangled…

机器学习 · 统计学 2019-12-12 Harshvardhan Sikka , Weishun Zhong , Jun Yin , Cengiz Pehlevan

In variational autoencoders (VAEs), the variational posterior often collapses to the prior, known as posterior collapse, which leads to poor representation learning quality. An adjustable hyperparameter beta has been introduced in VAEs to…

机器学习 · 统计学 2025-07-22 Yuma Ichikawa , Koji Hukushima

Variational Autoencoder (VAE), a simple and effective deep generative model, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. However, recent studies demonstrate that,…

机器学习 · 计算机科学 2019-01-08 Xuezhe Ma , Chunting Zhou , Eduard Hovy

Variational autoencoders (VAEs) are a powerful class of deep generative latent variable model for unsupervised representation learning on high-dimensional data. To ensure computational tractability, VAEs are often implemented with a…

机器学习 · 计算机科学 2020-06-09 Alex Campbell , Pietro Liò

Learning latent representations that are simultaneously expressive, geometrically well-structured, and reliably calibrated remains a central challenge for Variational Autoencoders (VAEs). Standard VAEs typically assume a diagonal Gaussian…

机器学习 · 计算机科学 2025-12-02 Mehmet Can Yavuz

The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-dimensional latent…

机器学习 · 统计学 2021-03-03 Marissa C. Connor , Gregory H. Canal , Christopher J. Rozell