- This event has passed.
Colloquium – Ji Liu
March 23 @ 3:30 pm - 5:20 pm
University of Rochester
March 23, 2017
Host: Aditya Bhaskara
Understanding the asynchronous parallelism in large scale machine learning
Asynchronous parallel algorithms recently received extensive attention and successes in deep learning, deep learning, recommendation system, high performance computing, and many other areas. While they usually significantly outperform the traditional naive synchronous parallel algorithms, their property and theoretical guarantee remain unclear. To better understand the behavior of AP, this talk will introduce a few work done by the speaker from practice to theoretical foundations.
Ji Liu is an assistant professor in Computer Science, Electrical and Computer Engineering, and Goergen Institute for Data Science at University of Rochester (UR). He received his Ph.D. in Computer Science from University of Wisconsin-Madison. His research interests focus on optimization and machine learning. He also has rich experiences in various data analytics applications in healthcare, bioinformatics, social network, computer vision, etc. His recent research focus is on asynchronous parallel optimization, sparse learning (compressed sensing) theory and algorithm, structural model estimation, online learning, abnormal event detection, feature / pattern extraction, etc. He published more than 30 papers in top CS journals and conferences including JMLR, SIOPT, TPAMI, TIP, TKDD, NIPS, ICML, UAI, SIGKDD, ICCV, CVPR, ECCV, AAAI, IJCAI, ACMMM, etc. He won the award of Best Paper honorable mention at SIGKDD 2010 and the award of Best Student Paper award at UAI 2015.