A Bayesian dynamic latent space model is introduced for weighted temporal networks with time-varying features, excess zeros, and an efficient multi-move sampler new to the network literature.
and ZHU, J
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 2polarities
background 2representative citing papers
SyNGLER generates synthetic networks by reconstructing latent embeddings with a distribution-free generator over learned node embeddings from latent space models, with consistency guarantees on edge distributions and better preservation of network moments and degrees than prior methods.
Unified framework relaxes spectral constraints and provides parameter-free guarantees linking practical algorithms to MLE for latent space network models.
A multi-stage smoothing estimator is developed to estimate time-varying network edge probabilities under Hölder smoothness and piecewise Lipschitz conditions.
Nonconvex low-rank matrix estimation procedures are shown to be equivalent to locally strongly convex formulations via a benign regularizer that does not change the algorithm's update rule.
citing papers explorer
-
A Bayesian Dynamic Latent Space Model for Weighted Networks
A Bayesian dynamic latent space model is introduced for weighted temporal networks with time-varying features, excess zeros, and an efficient multi-move sampler new to the network literature.
-
Efficient Synthetic Network Generation via Latent Embedding Reconstruction
SyNGLER generates synthetic networks by reconstructing latent embeddings with a distribution-free generator over learned node embeddings from latent space models, with consistency guarantees on edge distributions and better preservation of network moments and degrees than prior methods.
-
Bridging Theory and Practice: Statistical Inference for Latent Space Models of Networks
Unified framework relaxes spectral constraints and provides parameter-free guarantees linking practical algorithms to MLE for latent space network models.
-
Nonparametric estimation of time-varying network connections by multi-stage smoothing
A multi-stage smoothing estimator is developed to estimate time-varying network edge probabilities under Hölder smoothness and piecewise Lipschitz conditions.
-
Convexity in Disguise: A Theoretical Framework for Nonconvex Low-Rank Matrix Estimation
Nonconvex low-rank matrix estimation procedures are shown to be equivalent to locally strongly convex formulations via a benign regularizer that does not change the algorithm's update rule.