English
Related papers

Related papers: Decoder ensembling for learned latent geometries

200 papers

Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embedding data onto matching manifolds, it typically relies on an encoder to estimate densities on…

Machine Learning · Computer Science 2026-05-05 Andreas Bjerregaard , Søren Hauberg , Anders Krogh

Given data, deep generative models, such as variational autoencoders (VAE) and generative adversarial networks (GAN), train a lower dimensional latent representation of the data space. The linear Euclidean geometry of data space pulls back…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Line Kuhnel , Tom Fletcher , Sarang Joshi , Stefan Sommer

Deep generative models are tremendously successful in learning low-dimensional latent representations that well-describe the data. These representations, however, tend to much distort relationships between points, i.e. pairwise distances…

Machine Learning · Computer Science 2018-09-14 Tao Yang , Georgios Arvanitidis , Dongmei Fu , Xiaogang Li , Søren Hauberg

Latent manifolds of autoencoders provide low-dimensional representations of data, which can be studied from a geometric perspective. We propose to describe these latent manifolds as implicit submanifolds of some ambient latent space. Based…

Machine Learning · Computer Science 2026-01-30 Florine Hartwig , Josua Sassen , Juliane Braunsmann , Martin Rumpf , Benedikt Wirth

Measuring the similarity between data points often requires domain knowledge, which can in parts be compensated by relying on unsupervised methods such as latent-variable models, where similarity/distance is estimated in a more compact…

Machine Learning · Statistics 2020-08-13 Nutan Chen , Alexej Klushyn , Francesco Ferroni , Justin Bayer , Patrick van der Smagt

Deep generative models like variational autoencoders approximate the intrinsic geometry of high dimensional data manifolds by learning low-dimensional latent-space variables and an embedding function. The geometric properties of these…

Computer Vision and Pattern Recognition · Computer Science 2019-02-20 Ankita Shukla , Shagun Uppal , Sarthak Bhagat , Saket Anand , Pavan Turaga

Latent variable models are powerful tools for learning low-dimensional manifolds from high-dimensional data. However, when dealing with constrained data such as unit-norm vectors or symmetric positive-definite matrices, existing approaches…

Machine Learning · Computer Science 2025-03-10 Leonel Rozo , Miguel González-Duque , Noémie Jaquier , Søren Hauberg

Generative adversarial networks (GANs) have emerged as a powerful unsupervised method to model the statistical patterns of real-world data sets, such as natural images. These networks are trained to map random inputs in their latent space…

Machine Learning · Computer Science 2021-03-19 Binxu Wang , Carlos R. Ponce

Deep generative networks have been widely used for learning mappings from a low-dimensional latent space to a high-dimensional data space. In many cases, data transformations are defined by linear paths in this latent space. However, the…

Machine Learning · Statistics 2019-12-06 Marissa Connor , Christopher Rozell

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space. Under certain regularity conditions, these models parameterize nonlinear manifolds in the data space. In this paper, we investigate…

Machine Learning · Computer Science 2017-11-23 Hang Shao , Abhishek Kumar , P. Thomas Fletcher

A common assumption in generative models is that the generator immerses the latent space into a Euclidean ambient space. Instead, we consider the ambient space to be a Riemannian manifold, which allows for encoding domain knowledge through…

Machine Learning · Statistics 2020-08-04 Georgios Arvanitidis , Søren Hauberg , Bernhard Schölkopf

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local details with global…

Machine Learning · Computer Science 2025-05-08 Ren Wang , Pengcheng Zhou

Latent space geometry has shown itself to provide a rich and rigorous framework for interacting with the latent variables of deep generative models. The existing theory, however, relies on the decoder being a Gaussian distribution as its…

Machine Learning · Computer Science 2022-04-26 Georgios Arvanitidis , Miguel González-Duque , Alison Pouplin , Dimitris Kalatzis , Søren Hauberg

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

Graph Neural Networks usually rely on the assumption that the graph topology is available to the network as well as optimal for the downstream task. Latent graph inference allows models to dynamically learn the intrinsic graph structure of…

Machine Learning · Computer Science 2023-06-28 Haitz Sáez de Ocáriz Borde , Anees Kazi , Federico Barbero , Pietro Liò

Graph transformers typically embed every node in a single Euclidean space, blurring heterogeneous topologies. We prepend a lightweight Riemannian mixture-of-experts layer that routes each node to various kinds of manifold, mixture of…

Machine Learning · Computer Science 2025-07-11 Ankit Jyothish , Ali Jannesari

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…

Machine Learning · Statistics 2020-10-23 Clément Chadebec , Clément Mantoux , Stéphanie Allassonnière

Sparse autoencoders have become a standard tool for uncovering interpretable latent representations in neural networks. Yet salient concepts often span manifolds that current linear methods cannot capture without post hoc analysis. This…

Machine Learning · Computer Science 2026-05-12 Thomas Dooms , Ward Gauderis , Geraint Wiggins , Jose Oramas

Transformer models have consistently achieved remarkable results in various domains such as natural language processing and computer vision. However, despite ongoing research efforts to better understand these models, the field still lacks…

Machine Learning · Computer Science 2024-10-18 Ilya Kaufman , Omri Azencot
‹ Prev 1 2 3 10 Next ›