English
Related papers

Related papers: On the Identifiability of Quantized Factors

200 papers

We use a tensor unfolding technique to prove a new identifiability result for discrete bipartite graphical models, which have a bipartite graph between an observed and a latent layer. This model family includes popular models such as…

Statistics Theory · Mathematics 2025-01-22 Yuqi Gu

Learning disentangled representations from visual data, where different high-level generative factors are independently encoded, is of importance for many computer vision tasks. Solving this problem, however, typically requires to…

Computer Vision and Pattern Recognition · Computer Science 2019-01-25 Adria Ruiz , Oriol Martinez , Xavier Binefa , Jakob Verbeek

To improve the ability of VAE to disentangle in the latent space, existing works mostly focus on enforcing independence among the learned latent factors. However, the ability of these models to disentangle often decreases as the complexity…

Machine Learning · Computer Science 2019-09-05 Prashnna Kumar Gyawali , Zhiyuan Li , Cameron Knight , Sandesh Ghimire , B. Milan Horacek , John Sapp , Linwei Wang

Disentangling the explanatory factors in complex data is a promising approach for generalizable and data-efficient representation learning. While a variety of quantitative metrics for learning and evaluating disentangled representations…

Machine Learning · Computer Science 2024-11-01 Yivan Zhang , Masashi Sugiyama

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most…

We address the problem of person re-identification (reID), that is, retrieving person images from a large dataset, given a query image of the person of interest. A key challenge is to learn person representations robust to intra-class…

Computer Vision and Pattern Recognition · Computer Science 2019-11-04 Chanho Eom , Bumsub Ham

Biological phenotypes are products of complex evolutionary processes in which selective forces influence multiple biological trait measurements in unknown ways. Phylogenetic factor analysis disentangles these relationships across the…

We present a novel nonparametric algorithm for symmetry-based disentangling of data manifolds, the Geometric Manifold Component Estimator (GEOMANCER). GEOMANCER provides a partial answer to the question posed by Higgins et al. (2018): is it…

Machine Learning · Statistics 2020-11-19 David Pfau , Irina Higgins , Aleksandar Botev , Sébastien Racanière

Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…

Audio and Speech Processing · Electrical Eng. & Systems 2023-08-09 Michael Kuhlmann , Adrian Meise , Fritz Seebauer , Petra Wagner , Reinhold Haeb-Umbach

One of the fundamental representation learning tasks is unsupervised sequential disentanglement, where latent codes of inputs are decomposed to a single static factor and a sequence of dynamic factors. To extract this latent information,…

Machine Learning · Computer Science 2025-10-09 Nimrod Berman , Ilan Naiman , Idan Arbiv , Gal Fadlon , Omri Azencot

Latent traversal is a popular approach to visualize the disentangled latent representations. Given a bunch of variations in a single unit of the latent representation, it is expected that there is a change in a single factor of variation of…

Computer Vision and Pattern Recognition · Computer Science 2020-07-28 Xinqi Zhu , Chang Xu , Dacheng Tao

In many-body physics, renormalization techniques are used to extract aspects of a statistical or quantum state that are relevant at large scale, or for low energy experiments. Recent works have proposed that these features can be formally…

Machine Learning · Computer Science 2018-12-20 Cédric Bény

Identifying the underlying time-delayed latent causal processes in sequential data is vital for grasping temporal dynamics and making downstream reasoning. While some recent methods can robustly identify these latent causal variables, they…

Machine Learning · Computer Science 2024-05-31 Guangyi Chen , Yifan Shen , Zhenhao Chen , Xiangchen Song , Yuewen Sun , Weiran Yao , Xiao Liu , Kun Zhang

Domain generalization aims to learn an invariant model that can generalize well to the unseen target domain. In this paper, we propose to tackle the problem of domain generalization by delivering an effective framework named Variational…

Computer Vision and Pattern Recognition · Computer Science 2023-05-17 Yufei Wang , Haoliang Li , Hao Cheng , Bihan Wen , Lap-Pui Chau , Alex C. Kot

We introduce a method to disentangle controllable and uncontrollable factors of variation by interacting with the world. Disentanglement leads to good representations and is important when applying deep neural networks (DNNs) in fields…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Yoshihide Sawada

Decomposing complex data into factorized representations can reveal reusable components and enable synthesizing new samples via component recombination. We investigate this in the context of diffusion-based models that learn factorized…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Archer Wang , Emile Anand , Yilun Du , Marin Soljačić

This paper studies the estimation of characteristic-based quantile factor models where the factor loadings are unknown functions of observed individual characteristics while the idiosyncratic error terms are subject to conditional quantile…

Econometrics · Economics 2023-04-27 Liang Chen , Juan Jose Dolado , Jesus Gonzalo , Haozi Pan

Given a generalist model, learning a task-relevant specialist representation is fundamental for downstream applications. Identifiability, the asymptotic guarantee of recovering the ground-truth representation, is critical because it sets…

Machine Learning · Computer Science 2026-05-14 Yujia Zheng , Fan Feng , Yuke Li , Shaoan Xie , Kevin Murphy , Kun Zhang

Causal discovery from i.i.d. observational data is known to be generally ill-posed. We demonstrate that if we have access to the distribution {induced} by a structural causal model, and additional data from (in the best case) \textit{only…

Machine Learning · Statistics 2026-05-15 Francesco Montagna

The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we…

Machine Learning · Computer Science 2019-06-19 Francesco Locatello , Stefan Bauer , Mario Lucic , Gunnar Rätsch , Sylvain Gelly , Bernhard Schölkopf , Olivier Bachem