J. Lyle Kim

Ph.D. student in Computer Science

Rice University

Biography

My legal name is Junhyung Kim (김준형), but I usually go by Lyle. I am a third year Ph.D. student in Computer Science at Rice University, advised by Prof. Anastasios Kyrillidis.

Before joining Rice, I was a research professional at the University of Chicago Booth School of Business supervised by Prof. Panos Toulis and Prof. Sanjog Misra.

I received bachelor’s degrees in Mathematics and Statistics at the University of Chicago in 2017. During my senior year at the college, I also worked with Prof. Mikael Kuusela under the supervision of Prof. Michael L. Stein.

For Summer 2022, I will be joining Meta AI Research as a research intern under the supervision of Dr. Aaron Defazio.

Here is my CV.

Interests

Optimization
Distributed optimization
Machine learning
Quantum computing

Education

Ph.D. in Computer Science, 2019 - present

Rice University
B.A. in Mathematics; B.A. in Statistics, 2017

University of Chicago

News

[09 Jun 2022] Our paper “Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography” has been accepted at the IEEE Control Systems Letters (L-CSS), 2022. This is joint work with M. Taha Toghani, Prof. César A. Uribe, and Prof. Tasos Kyrillidis.

[09 May 2022] I started my research intenship at Meta AI Research under the supervision of Dr. Aaron Defazio.

[23 Mar 2022] Our new paper “Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography” is available on arXiv. This is joint work with M. Taha Toghani, Prof. César A. Uribe, and Prof. Tasos Kyrillidis.

[01 Mar 2022] Our paper “Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum” has been accepted at Learning for Dynamics and Control (L4DC) 2022.

[27 Oct 2021] I presented “Fast quantum state tomography via accelerated non-convex programming” at INFORMS 2021.

Research

Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis (2022). Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography. IEEE Control Systems Letters (L-CSS) 2022 (forthcoming).

Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis (2022). Convergence and Stability of the Stochastic Proximal Point Algorithm with Momentum. Learning for Dynamics and Control (L4DC) 2022 (forthcoming).

Junhyung Lyle Kim, Panos Toulis, Anastasios Kyrillidis (2021). Acceleration and Stability of the Stochastic Proximal Point Algorithm. Workshop on Optimization for Machine Learning, NeurIPS 2021 (spotlight).

Cameron Wolfe, Qihan Wang, Junhyung Lyle Kim, Anastasios Kyrillidis (2021). Provably efficient lottery ticket discovery. Under review.

Junhyung Lyle Kim, Jose Antonio Lara Benitez, Mohammad Taha Toghani, Cameron Wolfe, Zhiwei Zhang, Anastasios Kyrillidis (2021). Momentum-inspired low-rank coordinate descent for diagonally constrained SDPs. Under review.

Junhyung Lyle Kim, George Kollias, Amir Kalev, Ken X. Wei, Anastasios Kyrillidis (2021). Fast quantum state reconstruction via accelerated non-convex programming. Under review.

Preprint Code Slides Blog Press

Junhyung Lyle Kim, Mikael Kuusela (2019). Undersmoothed uncertainty quantification for unfolding. Technical Report.

Report Code Documentation