English
Related papers

Related papers: Disentanglement by Nonlinear ICA with General Inco…

200 papers

There is a gap between the theoretical foundations of disentanglement and the practice of modern representation learning. Existing theoretical frameworks, particularly Independent Component Analysis (ICA) and its nonlinear variants, assume…

Machine Learning · Computer Science 2026-05-22 Edmond Cunningham

A central problem in unsupervised deep learning is how to find useful representations of high-dimensional data, sometimes called "disentanglement". Most approaches are heuristic and lack a proper theoretical foundation. In linear…

Machine Learning · Computer Science 2023-09-06 Aapo Hyvarinen , Ilyes Khemakhem , Hiroshi Morioka

This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent factors of interest depend sparsely on past latent factors and/or observed auxiliary variables. We…

The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the data. Often, we're interested in going a step further, and…

Machine Learning · Statistics 2020-12-22 Ilyes Khemakhem , Diederik P. Kingma , Ricardo Pio Monti , Aapo Hyvärinen

Recently, nonlinear ICA has surfaced as a popular alternative to the many heuristic models used in deep representation learning and disentanglement. An advantage of nonlinear ICA is that a sophisticated identifiability theory has been…

Machine Learning · Statistics 2023-11-29 Hermanni Hälvä , Jonathan So , Richard E. Turner , Aapo Hyvärinen

We introduce a new general identifiable framework for principled disentanglement referred to as Structured Nonlinear Independent Component Analysis (SNICA). Our contribution is to extend the identifiability theory of deep generative models…

Causal discovery aims to recover causal structures or models underlying the observed data. Despite its success in certain domains, most existing methods focus on causal relations between observed variables, while in many scenarios the…

Machine Learning · Computer Science 2020-11-19 Feng Xie , Ruichu Cai , Biwei Huang , Clark Glymour , Zhifeng Hao , Kun Zhang

Nonlinear ICA is a fundamental problem for unsupervised representation learning, emphasizing the capacity to recover the underlying latent variables generating the data (i.e., identifiability). Recently, the very first identifiability…

Machine Learning · Statistics 2019-02-05 Aapo Hyvarinen , Hiroaki Sasaki , Richard E. Turner

Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…

Machine Learning · Computer Science 2024-10-08 Ruoyu Wang , Lina Yao

In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data. However, one of their weaknesses lies in their poor ability to…

Machine Learning · Computer Science 2022-03-08 Zehao Wang , Kaili Wang , Tinne Tuytelaars , Jose Oramas

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Aadhithya Sankar , Matthias Keicher , Rami Eisawy , Abhijeet Parida , Franz Pfister , Seong Tae Kim , Nassir Navab

Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. In this work, we consider data given as an invertible mixture of two statistically independent components and assume that…

Machine Learning · Statistics 2023-03-08 Uri Shaham , Jonathan Svirsky , Ori Katz , Ronen Talmon

Recent advances in nonlinear Independent Component Analysis (ICA) provide a principled framework for unsupervised feature learning and disentanglement. The central idea in such works is that the latent components are assumed to be…

Machine Learning · Statistics 2020-06-23 Hermanni Hälvä , Aapo Hyvärinen

Nonlinear independent component analysis (ICA) aims to recover the underlying independent latent sources from their observable nonlinear mixtures. How to make the nonlinear ICA model identifiable up to certain trivial indeterminacies is a…

Machine Learning · Computer Science 2024-02-27 Yujia Zheng , Ignavier Ng , Kun Zhang

We consider linear non-Gaussian structural equation models that involve latent confounding. In this setting, the causal structure is identifiable, but, in general, it is not possible to identify the specific causal effects. Instead, a…

Machine Learning · Statistics 2024-08-12 Daniela Schkoda , Elina Robeva , Mathias Drton

We introduce Nonlinear GENERIC Informed Neural Networks (N-GINNs), a deep learning framework for discovering evolution equations of systems governed by the nonlinear GENERIC formalism (General Equation for Non-Equilibrium…

Computational Physics · Physics 2026-05-12 Vojtěch Votruba , Zequn He , Weilun Qiu , Celia Reina , Michal Pavelka

Causal disentanglement aims to learn about latent causal factors behind data, holding the promise to augment existing representation learning methods in terms of interpretability and extrapolation. Recent advances establish identifiability…

Machine Learning · Computer Science 2024-12-25 Ryan Welch , Jiaqi Zhang , Caroline Uhler

In recent years, several methods have been proposed for the discovery of causal structure from non-experimental data (Spirtes et al. 2000; Pearl 2000). Such methods make various assumptions on the data generating process to facilitate its…

Machine Learning · Computer Science 2012-07-09 Shohei Shimizu , Aapo Hyvarinen , Yutaka Kano , Patrik O. Hoyer

Nearly all identifiability results in unsupervised representation learning inspired by, e.g., independent component analysis, factor analysis, and causal representation learning, rely on assumptions of additive independent noise or…

Machine Learning · Computer Science 2025-03-24 Yujia Zheng , Yang Liu , Jiaxiong Yao , Yingyao Hu , Kun Zhang

In this paper, we investigate the algorithmic stability of unsupervised representation learning with deep generative models, as a function of repeated re-training on the same input data. Algorithms for learning low dimensional linear…

Machine Learning · Computer Science 2022-07-05 Matthew Willetts , Brooks Paige
‹ Prev 1 2 3 10 Next ›