De Wen Soh received the B.S. degree in Mathematics from Stanford University. He received his Ph.D. degree in Electrical Engineering from Yale University under the supervision of Sekhar Tatikonda, where he worked on high-dimensional graphical model learning. In 2016, he joined the Institute of High Performance Computing, where he worked on machine learning research in relation to social and psychological sciences, alongside various industry projects associated with the consumer and transport industries. His research areas include graphical model estimation, graph signal processing, network analytics, transport modelling, high-dimensional statistical theory and artificial intelligence.
- H. E. Tan, D. W. Soh, and Y. S. Soh, “Reconstructing Train Logs from Smart Card Data using Passenger Correlations”, Transport Research Board 99th Annual Meeting, Jan 12 – 16, 2020.
- H. E. Tan, D. W. Soh, and Y. S. Soh, “General Method for Deriving Train Logs from Commuter Data Correlations”, Conference on Complex Systems, Sep 30 – Oct 4, 2019.
- Y. Yuan, D. W. Soh, H. Yang, and T. Q. S. Quek, “Learning Overlapping Community-based Networks”, IEEE Signal and Information Processing over Networks, 2019.
- D. W. Soh, and S. Tatikonda, “Learning Unfaithful K-separable Gaussian Graphical Models”, Journal of Machine Learning Research (JMLR), vol. 20, Issue 109, pp. 1-30, 2019.
- Y. Yuan, D. W. Soh, and T. Q. S. Quek, “Learning Graph with Overlapping Community Structure,” Proc. IEEE Int. Workshop on Signal Processing Adv. in Wireless Commun., Kalamata, GREECE, Jun. 2018.
- D. W. Soh, and S. Tatikonda, “Testing Unfaithful Gaussian Graphical Models”, Advances in Neural Information Processing Systems (NIPS) 27, pp. 2681-2689, 2014.
- D. W. Soh, T. Q. S. Quek, and W. P. Tay, “An Analysis of Randomized Broadcast Time in Dynamic Network Environments”, IEEE/ACM Trans. Networking, vol.21, no. 3, pp. 681-691, Jun 2013.