 |
Harry Dong
PhD Student, Carnegie Mellon University
I am an Electrical and Computer Engineering (ECE) PhD student at Carnegie Mellon University (CMU) where I have the pleasure of exploring my research interests in efficient machine learning algorithms with my advisor, Professor Yuejie Chi. Prior to CMU, I graduated with High Distinction from UC Berkeley with degrees in statistics and computer science in 2021. Please reach me through email: harryd [at] andrew [dot] cmu [dot] edu |
Research Overview
Powerful deep learning models, notably transformers, are becoming so large and slow that they are virtually impractical to use for many people. With the goal of making machine learning more accessible, I am currently focused on improving transformer efficiency by leveraging inherent structures and patterns within the architecture and data.
Projects
Hardware-aware Deep Learning: Efficient and hardware friendly algorithms/architectures to reduce inference complexity, with a focus on large transformer models.
Tensor Robust Principal Component Analysis: Low rank tensor recovery from sparsely corrupted data with theoretical guarantees and empirical analysis.
Machine Learning in Materials Science: Scalable methods for large tensor data that have underlying physics relationships.
Previous Projects
Traffic Routing: Optimal/stochastic vehicle routing in traffic networks.
Deep Learning for Neuroscience: Neuronal ion conductances prediction from voltage signals.
Awards
Liang Ji-Dian Graduate Fellowship (2023)
Michel and Kathy Doreau Graduate Fellowship in Electrical and Computer Engineering (2023)
NSF GRFP Honorable Mention (2023)