Youngsuk Park Office: Parkard 243, Stanford, CA 94305 |

My research interest lies in machine learning, optimization, and information theory. Especially, I develop methods related to modelings and algorithms in pursuit that machine learning problems can be solved with scalable and robust methods with theoretical guarantees.

Reinforcement Learning

Convergent Actor-Critic under Off-policy and Function Approximation.

*in preparation*.Adaptive Proximal Policy Optimization with a Saddle Point Method. Wokring Draft

Optimization

Linear Convergence of Cyclic SAGA. Y. Park, E. K. Ryu.

*submitted to Optimization Letter*.Variable Metric Proximal Gradient Method with Diagonal Barzilai-Borwein Stepsize. Y. Park, S. Dhar, M. Shah, S. Boyd.

*NIPS Workshop, Optimization for Machine Learning*, 2017

Probabilistic Graphical Model

Network Inference via the Time-Varying Graphical Lasso. D. Hallac, Y. Park, S. Boyd, J. Leskovec.

*ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)*, 2017 [Github]Learning the Network Structure of Heterogeneous Data via Pairwise Exponential Markov Random Fields. Y. Park, D. Hallac, S. Boyd, J. Leskovec.

*International Conference on Artificial Intelligence and Statistics (AISTATS)*, 2017 [Supplementary Material] [Github]

Information Theory

Universal Loseless Compression: Context Tree Weighting. [Slides]

Hypercontractivity, Maximal Correlation, and Non-cooperative Simulation. [Slides, Report]

Successive Lossy Compression for Laplacian Source. [Slides, Report]

Criteo Artificial Intelligence Labs, Research Scientist Intern, Summer 2018.

Bosch Center for Artificial Intelligence, Machine Learning Intern, Summer 2017.

Convex Optimization II, Teaching Assistance, Spring 2015

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

Hyundai Global Forum, 1st-rank Presenter in AI Session, 2018

Kwanjeong Graduate Fellowship, 2013–2015

Machine Learning: Artificial Intelligent (CS221), Machine Learning (CS229), Statistical Learning Theory (CS229T), Reinforcement Learning (CS234 and MS&E 338), etc.

Optimization: Convex Optimization 1 & 2, Introduction to Optimization Theory, Large-scale Numerical Optimization, etc.

Information Theory: Information Theory, Universal Schemes in Information Theory, Network Information Theory.

Statistics/Mathematics: Theory of Probability A, Theory of Statistics B, Numerical Linear Algebra, Real Analysis 1&2, Lebesque Integral, Differential Geometry, etc.