Neuro-Causal Factor Analysis (NCFA) reimagines traditional factor analysis by integrating causal structure learning and deep generative modeling. The method learns a directed graph linking latent and observed variables, then trains a deep generative model that respects the graph’s Markov factorization. Experiments on synthetic and real datasets show NCFA achieves lower reconstruction error than standard FA and better latent distribution recovery than a variational autoencoder, while offering a sparser architecture, reduced complexity, and causal interpretability.
By Alex Markham, Mingyu Liu, Bryon Aragam, Liam Solus
arXiv:2608. 16245v1 Announce Type: new Abstract: Disentangled representation learning seeks latent representations whose indicidual dimensions each align with a distinct covariate.
By Ma{\l}gorzata {\L}az\k{e}cka, Ewa Szczurek
arXiv:2602. 10680v2 Announce Type: replace-cross Abstract: Many real-world datasets contain hidden structure that cannot be detected by simple linear correlations between input features.
By Vicente Conde Mendes, Lorenzo Bardone, C\'edric Koller, Jorge Medina Moreira, Vittorio Erba, Emanuele Troiani, Lenka Zdeborov\'a
arXiv:2606. 08694v1 Announce Type: cross Abstract: Generative models are increasingly used to capture correlations in many-body systems, but the representations they learn remain largely opaque to physical interpretation.
By Marco Biroli, Max Welling, Vincenzo Vitelli
arXiv:2601. 18128v2 Announce Type: replace-cross Abstract: High-dimensional data often exhibit variation that can be captured by lower-dimensional factors.
By Gemma E. Moran, Anandi Krishnan
arXiv:2511. 13899v2 Announce Type: replace-cross Abstract: Low-rank recurrent neural networks (lrRNNs) are a class of models that uncover low-dimensional latent dynamics underlying neural population activity.
By Chengrui Li, Yunmiao Wang, Yule Wang, Weihan Li, Dieter Jaeger, Anqi Wu