SC20 Is Everywhere We Are

SC20 Virtual Platform
Biography
Wenqian is a Ph.D. candidate in Computer Science at the University of California, Merced. Her research focus on High-performance computing (large-scale parallel/distributed systems).

She is working on (i) Scientific machine learning: accelerating HPC applications using machine learning-based approximation, (ii) Automatic Machine Learning: automatically machine learning model construction for HPC ap-plications, and (iii) Automatic Performance Tuning: performance optimization and quality controlon accelerating HPC applications using machine learning-based approximation.
In this work, she uses innovative methods to make AI models interpretable and robust for accelerating a scientific application, power grid simulation. She proposes a iteractive learning model as information-sharing to predict multiple tasks and incorporate complex constraints imposed by physical principles to improve the interpretability and robustness of ML model. The results show that the simulation time is reduced by an average of 2.60×(up to 3.28×) without losing the optimality of the solution.
Presentations
Workshop
Education, Training and Outreach
Professional Development
Workforce Development
W
Workshop
Education, Training and Outreach
Professional Development
Workforce Development
W
Paper
Machine Learning, Deep Learning and Artificial Intelligence
Requirements, Performance, and Benchmarks
Reliability and Resiliency
TP
Back To Top Button