CoreFlow is a low-rank matrix generative model that trains normalizing flows on shared subspaces to improve efficiency and quality for high-dimensional limited-sample data, including incomplete matrices.
The geometry of algorithms with orthogonality constraints.SIAM journal on Matrix Analysis and Applications, 20(2):303–353
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
Task-irrelevant stimuli create long-term representational drift in task-relevant features, with drift rate increasing with variance and dimension of the irrelevant subspace, across Hebbian and gradient-based learning.
citing papers explorer
-
CoreFlow: Low-Rank Matrix Generative Models
CoreFlow is a low-rank matrix generative model that trains normalizing flows on shared subspaces to improve efficiency and quality for high-dimensional limited-sample data, including incomplete matrices.
-
Continuous Limits of Coupled Flows in Representation Learning
Discrete decentralized learning dynamics on manifolds converge uniformly to an overdamped Langevin SDE whose stationary states produce orthogonally disentangled, linearly separable features.
-
Contribution of task-irrelevant stimuli to drift of neural representations
Task-irrelevant stimuli create long-term representational drift in task-relevant features, with drift rate increasing with variance and dimension of the irrelevant subspace, across Hebbian and gradient-based learning.