English
Related papers

Related papers: On Latent Distributions Without Finite Mean in Gen…

200 papers

Diffusion models have achieved unprecedented performance in generative modeling. The commonly-adopted formulation of the latent code of diffusion models is a sequence of gradually denoised samples, as opposed to the simpler (e.g., Gaussian)…

Computer Vision and Pattern Recognition · Computer Science 2022-12-08 Chen Henry Wu , Fernando De la Torre

The use of Cauchy Markov random field priors in statistical inverse problems can potentially lead to posterior distributions which are non-Gaussian, high-dimensional, multimodal and heavy-tailed. In order to use such priors successfully,…

Computation · Statistics 2022-02-15 Neil K. Chada , Lassi Roininen , Jarkko Suuronen

This paper aims to conduct a comprehensive theoretical analysis of current diffusion models. We introduce a novel generative learning methodology utilizing the Schr{\"o}dinger bridge diffusion model in latent space as the framework for…

Machine Learning · Statistics 2024-12-24 Yuling Jiao , Lican Kang , Huazhen Lin , Jin Liu , Heng Zuo

This work addresses the distributed estimation problem in a set membership framework. The agents of a network collect measurements which are affected by bounded errors, thus implying that the unknown parameters to be estimated belong to a…

Optimization and Control · Mathematics 2018-12-11 Francesco Farina , Andrea Garulli , Antonio Giannitrapani

The recent success of neural network models has shone light on a rather surprising statistical phenomenon: statistical models that perfectly fit noisy data can generalize well to unseen test data. Understanding this phenomenon of…

Machine Learning · Statistics 2022-09-13 Niladri S. Chatterji , Philip M. Long , Peter L. Bartlett

The tabular form constitutes the standard way of representing data in relational database systems and spreadsheets. But, similarly to other forms, tabular data suffers from class imbalance, a problem that causes serious performance…

Machine Learning · Computer Science 2025-08-04 Leonidas Akritidis , Panayiotis Bozanis

In latent Dirichlet allocation (LDA), topics are multinomial distributions over the entire vocabulary. However, the vocabulary usually contains many words that are not relevant in forming the topics. We adopt a variable selection method…

Machine Learning · Computer Science 2012-05-08 Dongwoo Kim , Yeonseung Chung , Alice Oh

High-dimensional sample correlation matrices are a crucial class of random matrices in multivariate statistical analysis. The central limit theorem (CLT) provides a theoretical foundation for statistical inference. In this paper, assuming…

Statistics Theory · Mathematics 2024-08-30 Weijiang Chen , Shurong Zheng , Tingting Zou

Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last…

Machine Learning · Computer Science 2021-06-17 Xianghong Fang , Haoli Bai , Zenglin Xu , Michael Lyu , Irwin King

The Central Limit Theorem (CLT) is one of the most fundamental results in statistics. It states that the standardized sample mean of a sequence of $n$ mutually independent and identically distributed random variables with finite first and…

This paper considers binary classification of high-dimensional features under a postulated model with a low-dimensional latent Gaussian mixture structure and non-vanishing noise. A generalized least squares estimator is used to estimate the…

Machine Learning · Statistics 2023-03-30 Xin Bing , Marten Wegkamp

The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods…

Computation and Language · Computer Science 2020-07-03 Ping Cai , Xingyuan Chen , Peng Jin , Hongjun Wang , Tianrui Li

We propose a geometric latent-subspace framework for generative modeling of discrete data. Specifically, we introduce latent subspaces in the exponential parameter space of product manifolds of categorical distributions as a novel method…

Machine Learning · Statistics 2026-05-08 Daniel Gonzalez-Alvarado , Jonas Cassel , Stefania Petra , Christoph Schnörr

Diffusion models have become a standard approach for generative modeling in continuous domains, yet their application to discrete data remains challenging. We investigate why Gaussian diffusion models with the DDPM solver struggle to sample…

Computation and Language · Computer Science 2026-05-28 Alexander Shabalin , Simon Elistratov , Viacheslav Meshchaninov , Ildus Sadrtdinov , Dmitry Vetrov

Languages are not created randomly but rather to communicate information. There is a strong association between languages and their underlying meanings, resulting in a sparse joint distribution that is heavily peaked according to their…

Computation and Language · Computer Science 2023-09-15 Hui Jiang

The problem of inverse scattering proposed by Angles and Mallat in 2018, concerns training a deep neural network to invert the scattering transform applied to an image. After such a network is trained, it can be used as a generative model…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Juliusz Ziomek , Katayoun Farrahi

We investigate stochastic interpolation, a recently introduced framework for high dimensional sampling which bears many similarities to diffusion modeling. Stochastic interpolation generates a data sample by first randomly initializing a…

Statistics Theory · Mathematics 2025-10-28 Mara Daniels

Advances in generative models increase the need for sample quality assessment. To do so, previous methods rely on a pre-trained feature extractor to embed the generated samples and real samples into a common space for comparison. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Jingyi Xu , Hieu Le , Dimitris Samaras

We introduce Midpoint Generative Models (MGM), a principled framework for training one-step generative models. MGM is based on a simple symmetry of Flow Matching with linear interpolation: when the two endpoint distributions coincide, the…

Machine Learning · Computer Science 2026-05-29 Daniil Shlenskii , Nikita Gushchin , Lev Novitskiy , Dmitry V. Dylov , Alexander Korotin

We study the distribution of a fully connected neural network with random Gaussian weights and biases in which the hidden layer widths are proportional to a large constant $n$. Under mild assumptions on the non-linearity, we obtain…

Machine Learning · Computer Science 2024-06-18 Stefano Favaro , Boris Hanin , Domenico Marinucci , Ivan Nourdin , Giovanni Peccati