English
Related papers

Related papers: Markov Chain Decoders Overcome the Heavy-Tail Limi…

200 papers

Heavy-tailed distributions are ubiquitous in real-world data, where rare but extreme events dominate risk and variability. However, standard Variational Autoencoders (VAEs) employ simple decoder distributions, such as Gaussian…

Machine Learning · Computer Science 2026-05-27 Abdelhakim Ziani , András Horváth , Paolo Ballarini

Recent theoretical studies have shown that heavy-tails can emerge in stochastic optimization due to `multiplicative noise', even under surprisingly simple settings, such as linear regression with Gaussian data. While these studies have…

Machine Learning · Statistics 2025-05-06 Mert Gurbuzbalaban , Yuanhan Hu , Umut Simsekli , Kun Yuan , Lingjiong Zhu

Heavy-tailed distributions, prevalent in a lot of real-world applications such as finance, telecommunications, queuing theory, and natural language processing, are challenging to model accurately owing to their slow tail decay. Bernstein…

Performance · Computer Science 2025-10-31 Abdelhakim Ziani , András Horváth , Paolo Ballarini

Despite its success in a wide range of applications, characterizing the generalization properties of stochastic gradient descent (SGD) in non-convex deep learning problems is still an important challenge. While modeling the trajectories of…

Machine Learning · Statistics 2022-01-12 Umut Şimşekli , Ozan Sener , George Deligiannidis , Murat A. Erdogdu

The variational autoencoder (VAE) typically employs a standard normal prior as a regularizer for the probabilistic latent encoder. However, the Gaussian tail often decays too quickly to effectively accommodate the encoded points, failing to…

Machine Learning · Statistics 2024-03-05 Juno Kim , Jaehyuk Kwon , Mincheol Cho , Hyunjong Lee , Joong-Ho Won

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 of the variational…

Machine Learning · Statistics 2023-08-29 Marcel Hirt , Vasileios Kreouzis , Petros Dellaportas

Heavy-tailed distributions naturally occur in many real life problems. Unfortunately, it is typically not possible to compute inference in closed-form in graphical models which involve such heavy-tailed distributions. In this work, we…

Machine Learning · Computer Science 2011-03-22 Danny Bickson , Carlos Guestrin

We develop new flexible univariate models for light-tailed and heavy-tailed data, which extend a hierarchical representation of the generalized Pareto (GP) limit for threshold exceedances. These models can accommodate departure from…

Methodology · Statistics 2020-09-14 Rishikesh Yadav , Raphaël Huser , Thomas Opitz

Variational autoencoders (VAE) often use Gaussian or category distribution to model the inference process. This puts a limit on variational learning because this simplified assumption does not match the true posterior distribution, which is…

Machine Learning · Computer Science 2017-02-28 Ke Sun , Xiangliang Zhang

We consider a standard distributed optimization problem in which networked nodes collaboratively minimize the sum of their locally known convex costs. For this setting, we address for the first time the fundamental problem of design and…

Optimization and Control · Mathematics 2025-06-02 Manojlo Vukovic , Dusan Jakovetic , Dragana Bajovic , Soummya Kar

It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing…

Computer Vision and Pattern Recognition · Computer Science 2024-07-19 Mengke Li , Yiu-ming Cheung , Yang Lu , Zhikai Hu , Weichao Lan , Hui Huang

Although variational autoencoders (VAEs) represent a widely influential deep generative model, many aspects of the underlying energy function remain poorly understood. In particular, it is commonly believed that Gaussian encoder/decoder…

Machine Learning · Computer Science 2019-10-31 Bin Dai , David Wipf

Gradient compression has surfaced as a key technique to address the challenge of communication efficiency in distributed learning. In distributed deep learning, however, it is observed that gradient distributions are heavy-tailed, with…

Machine Learning · Computer Science 2024-02-07 Guangfeng Yan , Tan Li , Yuanzhang Xiao , Hanxu Hou , Linqi Song

In general, obtaining the exact steady-state distribution of queue lengths is not feasible. Therefore, we establish bounds for the tail probabilities of queue lengths. Specifically, we examine queueing systems under Heavy-Traffic (HT)…

Probability · Mathematics 2023-06-21 Prakirt Raj Jhunjhunwala , Daniela Hurtado-Lange , Siva Theja Maguluri

Markov Chain Monte Carlo methods become increasingly popular in applied mathematics as a tool for numerical integration with respect to complex and high-dimensional distributions. However, application of MCMC methods to heavy tailed…

Computation · Statistics 2020-01-01 Denis Belomestny , Leonid Iosipoi

Traditional implicit generative models are capable of learning highly complex data distributions. However, their training involves distinguishing real data from synthetically generated data using adversarial discriminators, which can lead…

Machine Learning · Computer Science 2025-09-05 José Manuel de Frutos , Manuel A. Vázquez , Pablo Olmos , Joaquín Míguez

Variational autoencoders (VAEs) are one of the deep generative models that have experienced enormous success over the past decades. However, in practice, they suffer from a problem called posterior collapse, which occurs when the encoder…

Machine Learning · Computer Science 2024-02-06 Yuri Kinoshita , Kenta Oono , Kenji Fukumizu , Yuichi Yoshida , Shin-ichi Maeda

This paper studies the distributed optimization problem under the influence of heavy-tailed gradient noises. Here, a heavy-tailed noise means that the noise does not necessarily satisfy the bounded variance assumption. Instead, it satisfies…

Optimization and Control · Mathematics 2025-05-12 Chao Sun , Huiming Zhang , Bo Chen , Li Yu

Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we…

Machine Learning · Statistics 2022-10-13 Antoine Salmona , Valentin de Bortoli , Julie Delon , Agnès Desolneux

A phase-type distribution is the distribution of the time until absorption in a finite state-space time-homogeneous Markov jump process, with one absorbing state and the rest being transient. These distributions are mathematically tractable…

Statistics Theory · Mathematics 2021-12-08 Martin Bladt , Jorge Yslas
‹ Prev 1 2 3 10 Next ›