Publications

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

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.
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe, Anastasios Kyrillidis
International Conference on Learning Representations (ICLR) 2024.

Preprint Poster

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

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

Pdf Blog Poster

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

Preprint

Undersmoothed Uncertainty Quantification for Unfolding.
Junhyung Lyle Kim, Mikael Kuusela
Technical Report, 2019.

Report Code Documentation