English
Related papers

Related papers: Statistical and structural identifiability in repr…

200 papers

Contrastive learning is a recent promising approach in unsupervised representation learning where a feature representation of data is learned by solving a pseudo classification problem from unlabelled data. However, it is not…

Machine Learning · Computer Science 2022-08-10 Hiroaki Sasaki , Takashi Takenouchi

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

We consider the identifiability theory of probabilistic models and establish sufficient conditions under which the representations learned by a very broad family of conditional energy-based models are unique in function space, up to a…

Machine Learning · Statistics 2020-10-27 Ilyes Khemakhem , Ricardo Pio Monti , Diederik P. Kingma , Aapo Hyvärinen

Finding overcomplete latent representations of data has applications in data analysis, signal processing, machine learning, theoretical neuroscience and many other fields. In an overcomplete representation, the number of latent features…

Machine Learning · Computer Science 2021-06-10 Jesse A. Livezey , Alejandro F. Bujan , Friedrich T. Sommer

Sequence data is challenging for machine learning approaches, because the lengths of the sequences may vary between samples. In this paper, we present an unsupervised learning model for sequence data, called the Integrated Sequence…

Computer Vision and Pattern Recognition · Computer Science 2018-04-30 Wenjie Pei , David M. J. Tax

Parametric system identification methods estimate the parameters of explicitly defined physical systems from data. Yet, they remain constrained by the need to provide an explicit function space, typically through a predefined library of…

Machine Learning · Computer Science 2026-03-17 Markus W. Baumgartner , Anson Lei , Joe Watson , Ingmar Posner

Model identifiability is a desirable property in the context of unsupervised representation learning. In absence thereof, different models may be observationally indistinguishable while yielding representations that are nontrivially related…

Machine Learning · Statistics 2022-02-15 Shubhangi Ghosh , Luigi Gresele , Julius von Kügelgen , Michel Besserve , Bernhard Schölkopf

A key goal of unsupervised representation learning is "inverting" a data generating process to recover its latent properties. Existing work that provably achieves this goal relies on strong assumptions on relationships between the latent…

Machine Learning · Computer Science 2021-11-01 Kartik Ahuja , Jason Hartford , Yoshua Bengio

The ability to recognize objects despite there being differences in appearance, known as Core Object Recognition, forms a critical part of human perception. While it is understood that the brain accomplishes Core Object Recognition through…

Machine Learning · Computer Science 2020-05-15 Harshvardhan Sikka

Learning Interpretable representation in medical applications is becoming essential for adopting data-driven models into clinical practice. It has been recently shown that learning a disentangled feature representation is important for a…

Machine Learning · Computer Science 2019-04-19 Mhd Hasan Sarhan , Abouzar Eslami , Nassir Navab , Shadi Albarqouni

Causal disentanglement aims to uncover a representation of data using latent variables that are interrelated through a causal model. Such a representation is identifiable if the latent model that explains the data is unique. In this paper,…

The interpretability of generative models is considered a key factor in demonstrating their effectiveness and controllability. The generated data are believed to be determined by latent variables that are not directly observable. Therefore,…

Machine Learning · Statistics 2025-08-14 Yuan-Hao Wei , Fu-Hao Deng , Lin-Yong Cui , Yan-Jie Sun

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades,…

Social and Information Networks · Computer Science 2019-02-13 Leonardo F. R. Ribeiro , Pedro H. P. Savarese , Daniel R. Figueiredo

While hidden class models of various types arise in many statistical applications, it is often difficult to establish the identifiability of their parameters. Focusing on models in which there is some structure of independence of some of…

Statistics Theory · Mathematics 2009-09-01 Elizabeth S. Allman , Catherine Matias , John A. Rhodes

In many data analysis tasks, it is beneficial to learn representations where each dimension is statistically independent and thus disentangled from the others. If data generating factors are also statistically independent, disentangled…

Machine Learning · Statistics 2019-12-12 Harshvardhan Sikka , Weishun Zhong , Jun Yin , Cengiz Pehlevan

We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…

Structural missingness breaks 'just impute and train': values can be undefined by causal or logical constraints, and the mask may depend on observed variables, unobserved variables (MNAR), and other missingness indicators. It simultaneously…

In this work, we propose the use of a causal collider structured model to describe the underlying data generative process assumptions in disentangled representation learning. This extends the conventional i.i.d. factorization assumption…

Machine Learning · Computer Science 2024-01-29 Juan Castorena

The performance of $\beta$-Variational-Autoencoders ($\beta$-VAEs) and their variants on learning semantically meaningful, disentangled representations is unparalleled. On the other hand, there are theoretical arguments suggesting the…

Machine Learning · Computer Science 2021-02-16 Dominik Zietlow , Michal Rolinek , Georg Martius

Independent Component Analysis (ICA) is an effective unsupervised tool to learn statistically independent representation. However, ICA is not only sensitive to whitening but also difficult to learn an over-complete basis. Consequently, ICA…

Computer Vision and Pattern Recognition · Computer Science 2013-04-10 Yanhui Xiao , Zhenfeng Zhu , Yao Zhao