PhD Candidate
University of Chicago
Areas of Interest
- Artificial Intelligence
- Computer Architecture and Engineering
- Operating Systems and Networking
Poster
Learning Structure for Computer Systems Management
Abstract
Modern computer systems expose diverse configurable parameters whose complicated interactions have surprising effects on performance and energy. This puts a great burden on systems designers and researchers to manage such complexity. Machine learning (ML) creates an opportunity to alleviate this burden by modeling resources' complicated, non-linear interactions and deliver an optimal solution to scheduling and resource management problems. However, naively applying traditional ML methods, such as deep learning, creates several challenges including generalization, robustness, and interpretability. A lack of generalizability and robustness in the ML models is largely due to the scarcity and bias of the training data. Causal inference creates an opportunity to tackle these challenges by analyzing observational data rather than data generated from randomized experiments. Since causal inference inherently studies the causal relationships---underlying structure---rather than correlation between features, it also provides interpretable systems results. This poster describes my PhD research on applying ML to systems along with key techniques from causal inference, characterizing my specific goals of: (1) learning for systems optimization with scarce data and system structure, and (2) learning for straggler prediction with imbalanced data.
Bio
Yi Ding is currently a final year PhD student in Computer Science from the University of Chicago. She is selected as a 2020 Computing Innovation Fellow by CRA/CCC/NSF. She is broadly interested in machine learning, causal inference, computer systems, and computer architecture. Her doctoral thesis topic is leveraging machine learning and causal inference to better understand modern computing systems so as to improve system outcomes. She has published as the leading author at conferences including ISCA, NeurIPS, AISTATS, AAAI, and ICDM. She received her bachelor degree in Electrical Engineering with highest honors from Beijing Jiaotong University.
