STATSCALE SEMINARS
CURRENT SEMINARS

2 July 2021 - 3-4pm UK time

Speaker: Kevin Lin (University of Pennsylvania)

Title: Time-varying stochastic block models, with application to understanding the dynamics of gene co-expression

Abstract - Single-cell data enables us to investigate how gene co-expression patterns change as cells develop across time. While this question is multifaceted, we focus on understanding the theory behind a particular subtask in this talk: clustering nodes across many undirected labeled graphs indexed by time, also known as multilayer networks. Specifically, we discuss two stochastic block model (SBM) settings: one where the true connectivities among the clusters change over time while the true nodes' cluster memberships are held fixed, and another where both the SBMs' true node memberships and cluster connectivities vary smoothly across time. Our estimator is based on averaging the appropriately-debiased squared adjacency matrices followed by spectral clustering, and we demonstrate how our theoretical results improve upon the existing regimes-of-consistency (in terms of clustering error) as well as the rates-of-convergence in the literature. These results demonstrate the interplay among the number of nodes and graphs, the graph sparsity, and the rate-of-change in true cluster memberships or cluster connectivities across layers. We then demonstrate how our estimator performs empirically on single-cell data. This is a joint work with Jing Lei.

To register your interest in accessing the StatScale Seminars, contact Dr Hyeyoung Maeng 

PREVIOUS SEMINARS

18 June 2021 - Runmin Wang (Southern Methodist University)

Dating the Break in High Dimensional Data


 

4 June 2021 -  Abolfazl Safikhani (University of Florida)

Multiple Change Point Detection in Reduced Rank High Dimensional Vector Autoregressive Models


 

21th May 2021 - Hao Ni (University College London)

Sig-Wasserstein Generative models to generate realistic synthetic time series

7th May 2021 - Lynna Chu (Iowa State University)

Sequential Change-point Detection for High-Dimensional and non-Euclidean Data


 

26th March 2021 - Hao Chen (UC Davis)

A universal event detection framework for neuropixels data

 


 

12th March 2021 - Sumanta Basu (Cornell University)

Learning Financial Networks with Graphical Models of Time Series Data

26th February 2021 - Eric Kolaczyk (Boston University)

How hard is it to work with a network `average'?

12th February 2021 - Matteo Barigozzi (Università di Bologna)
Quasi Maximum Likelihood Estimation and Inference of Large Approximate Dynamic Factor Models via the EM algorithm

29th January 2021 - Holger Dette (Ruhr-Universitaet Bochum)

Testing Relevant Hypotheses in Functional Time Series via Self-Normalization

4th December 2020 - Priyanga Dilini Talagala (University of Moratuwa)

Anomaly Detection in Streaming Time Series Data

 

 

20th November 2020 - Florian Pein (University of Cambridge)

About the loss function for cross-validation in change-point regression

 

 

6th November 2020 - Alex Aue (UC Davis)

Random matrix theory aids statistical inference in high dimensions

 

 

23rd October 2020 - Yoav Zemel (University of Cambridge)

Probabilistic approximations to optimal transport

 

 

9th October 2020 - Solt Kovacs (ETH Zurich)

Optimistic search strategy: change point detection for large-scale data via adaptive logarithmic queries

 

 

17th July 2020 - Tobias Kley (University of Bristol)

A new approach for open-end sequential change point monitoring

 

 

3rd July, 2020 - Claudia Kirch (Otto-von-Guericke University)

Functional change point detection for fMRI data 

 

 

19th June, 2020 - Martin Tveten (Dept. of Mathematics, University of Oslo)

Scalable changepoint and anomaly detection in cross-correlated data

 

 

5th June, 2020 - Yudong Chen (University of Cambridge)

High-dimensional, multiscale online changepoint detection