Shuyuan Wu
Medical University of South Carolina
8 Papers
3 Citations
Shuyuan Wu is an academic researcher from Medical University of South Carolina. The author has contributed to research in topics: Computer science & Estimator. The author has an hindex of 2, co-authored 2 publications.
Chat about Author
Papers
•Posted Content
XML4MAT: Inter-conversion between MatlabTMstructured variables and the markup language MbML
TL;DR: A new m-file library, XML4MAT, is introduced that supports the inter-conversion between any Matlab structured variable and a specialized extended markup language (XML), designated as MbML, and also includes functions to import non-MbML compliant XML structures.
3
Sequential one‐step estimator by sub‐sampling for customer churn analysis with massive data sets
TL;DR: In this article , a sequential one-step (SOS) estimation method was proposed for large-scale customer churn analysis, where data points need to be sampled only with uniform probabilities, and the sampling step is conducted repeatedly.
3
Quasi-Newton Updating for Large-Scale Distributed Learning
TL;DR: In this article , a distributed quasi-Newton (DQN) framework with excellent statistical, computation, and communication efficiency was developed. But the proposed method requires a diverging number of iterations to converge.
2
Adaptive Decentralized Federated Learning for Robust Optimization
Shuyuan Wu,Feifei Wang,Yuan Gao,Rui Wang,Hansheng Wang +4 more
TL;DR: This paper proposes adaptive decentralized federated learning (aDFL) to mitigate the impact of abnormal clients on model robustness, without requiring prior knowledge or a large number of normal clients, and demonstrates its superior performance through rigorous convergence analysis and numerical experiments.
Optimal cDNA microarray design using expressed sequence tags for organisms with limited genomic information
Yian Ann Chen,David J. McKillen,Shuyuan Wu,Matthew J. Jenny,R. W. Chapman,R. W. Chapman,Paul S. Gross,Gregory W. Warr,Jonas S. Almeida +8 more
TL;DR: A general design procedure to select a subset of ESTs that will minimize sequence redundancy and characterize potential cross-hybridization while providing functionally representative probes is described.