Youngsuk Park
 |
Ph.D. Candidate Office: Parkard 243, Stanford, CA 94305 |
News
I defended with “Topics in Convex Optimization for Machine Learning.”
Feb. 2020. Our paper “Structured Policy Iteration for Linear Quadratic Regulator” was submitted to ICML.
Jan. 2020. Our paper “Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize.” was accepted to ICASSP.
Jan. 2020. Our paper “Optimal Operation of a Plug-in Hybrid Vehicle with Battery Thermal and Degradation Model.” was accepted to ACC.
Jan. 2020. Our paper “Linear Convergence of Cyclic SAGA.” was published in Optimization Letter.
Research Interests
Machine Learning
Optimization
Reinforcement Learning and Control
Information Theory
Experiences
Adobe Research, Data Science Research Intern, Summer 2019.
Reinforcement learning for continuous space task with cloud resource management application.
Criteo Artificial Intelligence Labs, Research Scientist Intern, Summer 2018.
Off-policy reinforcement learning with the application in advertisement recommendation system.
Bosch Center for Artificial Intelligence, Machine Learning Intern, Summer 2017.
Diagonal spectral stepsize selection for solving machine learning problems.
Convex Optimization II, Teaching Assistance, Spring 2015.
Education
Ph.D. Candidate, Electrical Engineering, Stanford University, In Progress
M.S., Electrical Engineering, Stanford University, 2016
B.S., Electrical Engineering, Minor in Mathematics, Korea Advanced Institute of Science and Technology, 2013
Honor
Hyundai Global Forum, 1st-rank Presenter in AI Session, 2018
Kwanjeong Graduate Fellowship, 2013–2015
Fulbright Fellowship (Declined)