English
Related papers

Related papers: Distributional Autoencoders Know the Score

200 papers

We seek a generalization of regression and principle component analysis (PCA) in a metric space where data points are distributions metrized by the Wasserstein metric. We recast these analyses as multimarginal optimal transport problems.…

Optimization and Control · Mathematics 2020-04-20 Amirhossein Karimi , Luigia Ripani , Tryphon T. Georgiou

Deep generative models offer powerful tools for multivariate data analysis, but their black-box architectures are often unidentified and difficult to interpret. We introduce the Deep Discrete Encoder (DDE) Copula, an identifiable and…

Machine Learning · Statistics 2026-05-28 Joseph Feldman , Yuqi Gu

In this paper, we consider the problem of distributed parameter estimation in sensor networks. Each sensor makes successive observations of an unknown $d$-dimensional parameter, which might be subject to Gaussian random noises. The sensors…

Signal Processing · Electrical Eng. & Systems 2025-01-20 Jiaqi Yan , Hideaki Ishii

Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the (aggregate) posterior to encourage statistical independence of the latent factors. This approach introduces a trade-off between…

Disentangling complex data to its latent factors of variation is a fundamental task in representation learning. Existing work on sequential disentanglement mostly provides two factor representations, i.e., it separates the data to…

Machine Learning · Computer Science 2023-03-31 Nimrod Berman , Ilan Naiman , Omri Azencot

Kernel Principal Component Analysis (KPCA) is a key machine learning algorithm for extracting nonlinear features from data. In the presence of a large volume of high dimensional data collected in a distributed fashion, it becomes very…

Machine Learning · Computer Science 2016-02-16 Maria-Florina Balcan , Yingyu Liang , Le Song , David Woodruff , Bo Xie

This paper considers the estimation and inference of the low-rank components in high-dimensional matrix-variate factor models, where each dimension of the matrix-variates ($p \times q$) is comparable to or greater than the number of…

Statistics Theory · Mathematics 2022-10-20 Elynn Y. Chen , Jianqing Fan

This work develops problem statements related to encoders and autoencoders with the goal of elucidating variational formulations and establishing clear connections to information-theoretic concepts. Specifically, four problems with varying…

Information Theory · Computer Science 2021-07-15 Karthik Duraisamy

Autoencoders have demonstrated remarkable success in learning low-dimensional latent features of high-dimensional data across various applications. Assuming that data are sampled near a low-dimensional manifold, we employ chart…

Machine Learning · Statistics 2023-10-26 Hao Liu , Alex Havrilla , Rongjie Lai , Wenjing Liao

Variational autoencoders (VAEs) learn representations of data by jointly training a probabilistic encoder and decoder network. Typically these models encode all features of the data into a single variable. Here we are interested in learning…

Autoencoders have seen wide success in domains ranging from feature selection to information retrieval. Despite this success, designing an autoencoder for a given task remains a challenging undertaking due to the lack of firm intuition on…

Neural and Evolutionary Computing · Computer Science 2020-04-17 Jeff Hajewski , Suely Oliveira , Xiaoyu Xing

The (variational) graph auto-encoder is widely used to learn representations for graph-structured data. However, the formation of real-world graphs is a complicated and heterogeneous process influenced by latent factors. Existing encoders…

Machine Learning · Computer Science 2024-07-17 Di Fan , Chuanhou Gao

The development of optimal and efficient machine learning-based communication systems is likely to be a key enabler of beyond 5G communication technologies. In this direction, physical layer design has been recently reformulated under a…

Information Theory · Computer Science 2021-11-16 Nunzio A. Letizia , Andrea M. Tonello

One develops a fast computational methodology for principal component analysis on manifolds. Instead of estimating intrinsic principal components on an object space with a Riemannian structure, one embeds the object space in a numerical…

Methodology · Statistics 2024-10-04 Ka Chun Wong , Vic Patrangenaru , Robert L. Paige , Mihaela Pricop Jeckstadt

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. It is structurally distinct from dispersion, yet…

Machine Learning · Statistics 2026-05-12 Shaul Tolkovsky , Ori Meidler , Or Zuk

Generative processes in biology and other fields often produce data that can be regarded as resulting from a composition of basic features. Here we present an unsupervised method based on autoencoders for inferring these basic features of…

Quantitative Methods · Quantitative Biology 2019-10-04 Matteo Negri , Davide Bergamini , Carlo Baldassi , Riccardo Zecchina , Christoph Feinauer

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the…

Machine Learning · Computer Science 2026-05-14 Akhil Premkumar , Sarah Lucioni

Score-based methods, such as diffusion models and Bayesian inverse problems, are often interpreted as learning the data distribution in the low-noise limit ($\sigma \to 0$). In this work, we propose an alternative perspective: their success…

Machine Learning · Statistics 2026-03-17 Xiang Li , Zebang Shen , Ya-Ping Hsieh , Niao He

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principal directions but…

Machine Learning · Computer Science 2019-05-15 Daniel Kunin , Jonathan M. Bloom , Aleksandrina Goeva , Cotton Seed

For discrete data, the likelihood $P(x)$ can be rewritten exactly and parametrized into $P(X = x) = P(X = x | H = f(x)) P(H = f(x))$ if $P(X | H)$ has enough capacity to put no probability mass on any $x'$ for which $f(x')\neq f(x)$, where…

Machine Learning · Statistics 2014-10-03 Sherjil Ozair , Yoshua Bengio
‹ Prev 1 4 5 6 7 8 10 Next ›