P
Pan Zhang
Researcher at Chinese Academy of Sciences
Publications - 139
Citations - 2980
Pan Zhang is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Computer science & Biology. The author has an hindex of 22, co-authored 74 publications receiving 2202 citations. Previous affiliations of Pan Zhang include ESPCI ParisTech & Centre national de la recherche scientifique.
Papers
More filters
Journal ArticleDOI
Spectral redemption in clustering sparse networks
Florent Krzakala,Cristopher Moore,Elchanan Mossel,Joe Neeman,Allan Sly,Lenka Zdeborová,Pan Zhang +6 more
TL;DR: A way of encoding sparse data using a “nonbacktracking” matrix, and it is shown that the corresponding spectral algorithm performs optimally for some popular generative models, including the stochastic block model.
Journal ArticleDOI
Scalable detection of statistically significant communities and hierarchies, using message passing for modularity
Pan Zhang,Cristopher Moore +1 more
TL;DR: By applying the proposed algorithm recursively, subdividing communities until no statistically significant subcommunities can be found, it is shown that the algorithm can detect hierarchical structure in real-world networks more efficiently than previous methods.
Journal ArticleDOI
Solving Statistical Mechanics Using Variational Autoregressive Networks.
TL;DR: This work proposes a general framework for solving statistical mechanics of systems with finite size using autoregressive neural networks, which computes variational free energy, estimates physical quantities such as entropy, magnetizations and correlations, and generates uncorrelated samples all at once.
Journal ArticleDOI
Unsupervised Generative Modeling Using Matrix Product States
TL;DR: In this article, the probability distribution of complex data using insights from quantum physics is modelled using GNNs, which shows great potential compared to conventional neural network approaches, and is a fresh approach to generative modeling in machine learning.
Journal ArticleDOI
Model selection for degree-corrected block models
Xiaoran Yan,Cosma Rohilla Shalizi,Jacob E. Jensen,Florent Krzakala,Cristopher Moore,Lenka Zdeborová,Pan Zhang,Yaojia Zhu +7 more
TL;DR: The first principled and tractable approach to model selection between standard and degree-corrected block models is presented, based on new large-graph asymptotics for the distribution of log-likelihood ratios under the stochastic block model, finding substantial departures from classical results for sparse graphs.