Lie Group VAE framework diagnoses latent non-commutativity through algebraic and reconstruction diagnostics then calibrates a stability constraint to align decoder behavior, showing improved consistency on dSprites, 3DShapes, 3DCars and CelebA versus beta-VAE, CLG-VAE and CFASL baselines.
Journal of Machine Learning Research , year =
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
A metric learning method is introduced to learn distance metrics that best capture conditional anomaly patterns in instance-based detection.
Instance-based conditional anomaly detection with optimized distance metrics detects unusual patient-management decisions in two real-world medical datasets.
citing papers explorer
-
Commutator-Induced Uncertainty in VAEs
Lie Group VAE framework diagnoses latent non-commutativity through algebraic and reconstruction diagnostics then calibrates a stability constraint to align decoder behavior, showing improved consistency on dSprites, 3DShapes, 3DCars and CelebA versus beta-VAE, CLG-VAE and CFASL baselines.
-
Distance metric learning for conditional anomaly detection
A metric learning method is introduced to learn distance metrics that best capture conditional anomaly patterns in instance-based detection.
-
Conditional anomaly detection methods for patient-management alert systems
Instance-based conditional anomaly detection with optimized distance metrics detects unusual patient-management decisions in two real-world medical datasets.