Fast Multigroup Gaussian Process Factor Models
Neural Computation · 08.08.2025 · 37 (9) · 1709-1782
DOI: 10.1162/neco.a.22 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computation, online erschienen am 08.08.2025. Verfasst von Evren Gokcen und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA egokcen@cmu.edu. Hauptthemen laut MEDLINE: Neurons, Models, Neurological, Brain. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 78 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NEI NIH HHS, NINDS NIH HHS.
Abstract (Originalsprache)
Gaussian processes are now commonly used in dimensionality reduction approaches tailored to neuroscience, especially to describe changes in high-dimensional neural activity over time. As recording capabilities expand to include neuronal populations across multiple brain areas, cortical layers, and cell types, interest in extending gaussian process factor models to characterize multipopulation interactions has grown. However, the cubic runtime scaling of current methods with the length of experimental trials and the number of recorded populations (groups) precludes their application to large-scale multipopulation recordings. Here, we improve this scaling from cubic to linear in both trial length and group number. We present two approximate approaches to fitting multigroup gaussian process factor models based on inducing variables and the frequency domain. Empirically, both methods achieved orders of magnitude speed-up with minimal impact on statistical performance, in simulation and on neural recordings of hundreds of neurons across three brain areas. The frequency domain approach, in particular, consistently provided the greatest runtime benefits with the fewest trade-offs in statistical performance. We further characterize the estimation biases introduced by the frequency domain approach and demonstrate effective strategies to mitigate them. This work enables a powerful class of analysis techniques to keep pace with the growing scale of multipopulation recordings, opening new avenues for exploring brain function.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA egokcen@cmu.edu.
- Dominick Purpura Department of Neuroscience, Albert Einstein College of Medicine, Bronx, NY 10461, USA anna.jasper@einsteinmed.edu.
- Dominick Purpura Department of Neuroscience, Department of Ophthalmology and Visual Sciences, and Department of Systems and Computational Biology, Albert Einstein College of Medicine, Bronx, NY 10461, USA adam.kohn@eins…
- Champalimaud Neuroscience Programme, Champalimaud Foundation, 1400-038 Lisbon, Portugal christian.machens@neuro.fchampalimaud.org.
- Department of Electrical and Computer Engineering and Department of Biomedical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA byronyu@cmu.edu.
Förderung
- NEI NIH HHS
- NINDS NIH HHS
Zitieren
APA
Gokcen, E., Jasper, A. I., Kohn, A., Machens, C. K., & Yu, B. M. (2025). Fast Multigroup Gaussian Process Factor Models. Neural Computation, 37(9), 1709-1782. https://doi.org/10.1162/neco.a.22
Vancouver
Gokcen E, Jasper AI, Kohn A, Machens CK, Yu BM. Fast Multigroup Gaussian Process Factor Models. Neural Computation. 2025;37(9):1709-1782. doi:10.1162/neco.a.22
BibTeX
@article{Gokcen2025,
author = {Gokcen, Evren and Jasper, Anna I and Kohn, Adam and Machens, Christian K and Yu, Byron M},
title = {Fast Multigroup Gaussian Process Factor Models},
journal = {Neural Computation},
year = {2025},
volume = {37},
number = {9},
pages = {1709--1782},
doi = {10.1162/neco.a.22}
}
EUVIMED