J. Lyle Kim

J. Lyle Kim

Quantum Computing Research Scientist

JPMorgan Chase, Global Technology Applied Research

Biography

I am a Quantum Computing Research Scientist – Sr. Associate at JPMorgan Chase, Global Technology Applied Research. I obtained a Ph.D in Computer Science from Rice University, where I was advised by Prof. Anastasios Kyrillidis. I also worked closely with Prof. César A. Uribe and Prof. Nai-Hui Chia.

During graduate school, I interned at JPMorgan Chase hosted by Dr. Marco Pistoia, at MILA – Quebec Artificial Intelligence Institute hosted by Prof. Gauthier Gidel and Prof. Ioannis Mitliagkas, and at Meta (Fundamental AI Research) hosted by Dr. Aaron Defazio.

Before joining Rice, I was a research professional at the University of Chicago Booth School of Business supervised by Prof. Panos Toulis, after receiving bachelor’s degrees in Mathematics and Statistics from the University of Chicago.

Here is my CV, and Google Scholar.

Interests

  • Optimization
  • Quantum computing / algorithms
  • Machine learning

Education

  • Ph.D. in Computer Science, 2019 - 2024

    Rice University

  • B.A. in Mathematics; B.A. in Statistics, 2017

    University of Chicago

News

See all news»

[01 Oct 2024] I started working as a quantum computing research scientist – Sr. Associate at JP Morgan Chase, Global Technology Applied Research.

[31 Aug 2024] I obtained my Ph.D. in Computer Science from Rice University. I am extremely grateful to my advisor Prof. Anastasios Kyrillidis and my committee members Prof. César A. Uribe, and Prof. Nai-Hui Chia.

[03 Jun 2024] I started my quantum computing research internship at JP Morgan Chase under the supervision of Dr. Marco Pistoia.

[23 Apr 2024] I succesfully defended! My defense slides are available here.

[01 May 2024] Our paper On the Error-Propagation of Inexact Deflation for Principal Component Analysis has been accepted at ICML 2024. Congratulations to all the co-authors!

Research

See all publications»

On the Error-Propagation of Inexact Deflation for Principal Component Analysis.
Fangshuo Liao, Junhyung Lyle Kim, Cruz Barnum, Anastasios Kyrillidis
International Conference on Machine Learning (ICML) 2024.

Preprint

Smoothness-Adaptive Sharpness-Aware Minimization for Finding Flatter Minima.
Hiroki Naganuma, Junhyung Lyle Kim, Anastasios Kyrillidis, Ioannis Mitliagkas
Practical Machine Learning for Low Resource Settings Workshop, ICLR 2024.

OpenReview Poster

How Much Pre-training Is Enough to Discover a Good Subnetwork?.
Cameron Wolfe, Fangshuo Liao, Qihan Wang, Junhyung Lyle Kim, Anastasios Kyrillidis
Transactions on Machine Learning Research (TMLR) 2024.

OpenReview Preprint

Adaptive Federated Learning with Auto-Tuned Clients.
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis
International Conference on Learning Representations (ICLR) 2024.

Preprint Poster

When is Momentum Extragradient Optimal? A Polynomial-Based Analysis.
Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis, Fabian Pedregosa
Transactions on Machine Learning Research (TMLR) 2024.

OpenReview Preprint

Adaptive Federated Learning with Auto-Tuned Clients via Local Smoothness.
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis
Federated Learning and Analytics in Practice: Algorithms, Systems, Applications, and Opportunities Workshop, ICML 2023.

Pdf Poster

Fast Quantum State Tomography via Accelerated Non-convex Programming.
Junhyung Lyle Kim, George Kollias, Amir Kalev, Ken X. Wei, Anastasios Kyrillidis
Photonics 2023, 10(2), 116 / Quantum Information Processing (QIP) 2023 (poster).

Pdf Preprint Code Slides Poster Blog Press

Momentum Extragradient is Optimal for Games with Cross-Shaped Spectrum.
Junhyung Lyle Kim, Gauthier Gidel, Anastasios Kyrillidis, Fabian Pedregosa
Workshop on Optimization for Machine Learning, NeurIPS 2022.

Pdf Poster

Local Stochastic Factored Gradient Descent for Distributed Quantum State Tomography.
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis
IEEE Control Systems Letters 2022 / Quantum Information Processing (QIP) 2023 (poster).

Pdf Preprint Poster

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

Pdf Preprint Blog Poster

See all publications

Contact