Books
Journal and conference publications
- Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique. T. Yoon, J. Kim, J. J. Suh, E. K. Ryu, Manuscript, 2024.
- LoRA Training in the NTK Regime has No Spurious Local Minima. U. Jang, J. D. Lee, and E. K. Ryu, Manuscript, 2024.
- Optimal First-Order Algorithms as a Function of Inequalities. C. Park and E. K. Ryu, Journal of Machine Learning Research, 2024.
- Image Clustering Conditioned on Text Criteria. S. Kwon, J. Park, M. Kim, J. Cho, E. K. Ryu, and K. Lee, International Conference on Learning Representations, 2024.
- Branch-and-Bound Performance Estimation Programming: A Unified Methodology for Constructing Optimal Optimization Methods. S. Das Gupta, B. P. G. Van Parys, and E. K. Ryu, Mathematical Programming Series A, 2024.
- Mirror Duality in Convex Optimization. J. Kim, C. Park, A. Ozdaglar, J. Diakonikolas, and E. K. Ryu, Manuscript, 2023.
- Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback. T. Yoon, K. Myoung, K. Lee, J. Cho, A. No, and E. K. Ryu, Neural Information Processing Systems, 2023.
- Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value. J. Kim, A. Ozdaglar, C.Park, and E. K. Ryu, Neural Information Processing Systems, 2023.
- Accelerating Value Iteration with Anchoring. J. Lee and E. K. Ryu, Neural Information Processing Systems, 2023.
- Continuous-Time Analysis of Anchor Acceleration. J. J. Suh, J. Park, and E. K. Ryu, Neural Information Processing Systems, 2023.
- Computer-Assisted Design of Accelerated Composite Optimization Methods: OptISTA. U. Jang, S. Das Gupta, and E. K. Ryu, Manuscript, 2023.
- Coordinate-Update Algorithms can Efficiently Detect Infeasible Optimization Problems. J. Paeng, J. Park, and E. K. Ryu, Manuscript, 2023.
- Rotation and Translation Invariant Representation Learning with Implicit Neural Representations. S. Kwon, J. Y. Choi, and E. K. Ryu, International Conference on Machine Learning, 2023.
- Accelerated Infeasibility Detection of Constrained Optimization and Fixed-Point Iterations. J. Park and E. K. Ryu, International Conference on Machine Learning, 2023.
- Factor-$\sqrt{2}$ Acceleration of Accelerated Gradient Methods. C. Park, J. Park, and E. K. Ryu, Applied Mathematics & Optimization, 2023.
- Convergence Analyses of Davis–Yin Splitting via Scaled Relative Graphs II: Convex Optimization Problems. S. Yi and E. K. Ryu, Manuscript, 2022.
- Convergence Analyses of Davis–Yin Splitting via Scaled Relative Graphs. J. Lee, S. Yi, and E. K. Ryu, Under revision at SIAM Journal on Optimization, 2022.
- Accelerated Minimax Algorithms Flock Together. T. Yoon and E. K. Ryu, Under revision at SIAM Journal on Optimization, 2022.
- Exact Optimal Accelerated Complexity for Fixed-Point Iterations. J. Park and E. K. Ryu, International Conference on Machine Learning (long presentation, top 118/5630=2% of papers), 2022.
- Continuous-Time Analysis of AGM via Conservation Laws in Dilated Coordinate Systems. J. J. Suh, G. Roh, and E. K. Ryu, International Conference on Machine Learning (long presentation, top 118/5630=2% of papers), 2022.
- Neural Tangent Kernel Analysis of Deep Narrow Neural Networks. J. Lee, J. Y. Choi, E. K. Ryu, and A. No, International Conference on Machine Learning, 2022.
- Robust Probabilistic Time Series Forecasting. T. Yoon, Y. Park, E. K. Ryu, and Y. Wang, International Conference on Artificial Intelligence and Statistics, 2022.
- Scaled Relative Graph: Nonexpansive operators via 2D Euclidean Geometry. E. K. Ryu, R. Hannah, and W. Yin, Mathematical Programming Series A, 2022.
- A Geometric Structure of Acceleration and Its Role in Making Gradients Small Fast. J. Lee, C. Park, and E. K. Ryu, Neural Information Processing Systems, 2021.
- Accelerated Algorithms for Smooth Convex-Concave Minimax Problems with $\mathcal{O}(1/k^2)$ Rate on Squared Gradient Norm. T. Yoon and E. K. Ryu, International Conference on Machine Learning (long presentation, top 166/5513=3% of papers), 2021.
- WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points. A. No, T. Yoon, S. Kwon, and E. K. Ryu, International Conference on Machine Learning, 2021.
- Decentralized Proximal Gradient Algorithms with Linear Convergence Rates. S. A. Alghunaim, E. K. Ryu, K. Yuan, and A. H. Sayed, IEEE Transactions on Automatic Control, 2021.
- Tight Coefficients of Averaged Operators via Scaled Relative Graph. X. Huang, E. K. Ryu, and W. Yin, Journal of Mathematical Analysis and Applications, 2020.
- Scaled Relative Graph of Normal Matrices. X. Huang, E. K. Ryu, and W. Yin, Manuscript.
- Operator Splitting Performance Estimation: Tight Contraction Factors and Optimal Parameter Selection. E. K. Ryu, A. B. Taylor, C. Bergeling, P. Giselsson, SIAM Journal on Optimization, 2020. Code.
- Splitting with Near-Circulant Linear Systems: Applications to Total Variation CT and PET. E. K. Ryu, S. Ko, and J.-H. Won, SIAM Journal on Scientific Computing, 2020. Code, Slides.
- Linear Convergence of Cyclic SAGA. Y. Park, E. K. Ryu, Optimization Letters, 2020.
- Finding the Forward-Douglas-Rachford-Forward Method. E. K. Ryu and B. C. Vũ, Journal of Optimization Theory and Applications, 2020.
- Uniqueness of DRS as the 2 Operator Resolvent-Splitting and Impossibility of 3 Operator Resolvent-Splitting. E. K. Ryu, Mathematical Programming Series A, 2020. Slides, Video (Overview), Video (Proof of Theorem 1), Video (Proof of Theorem 2), Video (Proof of Theorem 3), Video (Proof of Theorem 4).
- Plug-and-Play Methods Provably Converge with Properly Trained Denoisers. E. K. Ryu, J. Liu, S. Wang, X. Chen, Z. Wang, and W. Yin, International Conference on Machine Learning, 2019. Code, Slides, Video.
- Douglas-Rachford Splitting and ADMM for Pathological Convex Optimization. E. K. Ryu, Y. Liu, and W. Yin, Computational Optimization and Applications, 2019. Slides.
- A New Use of Douglas-Rachford Splitting for Identifying Infeasible, Unbounded, and Pathological Conic Programs. Y. Liu, E. K. Ryu, and W. Yin, Mathematical Programming Series A, 2019.
- Vector and Matrix Optimal Mass Transport: Theory, Algorithm, and Applications. E. K. Ryu, Y. Chen, W. Li, and S. Osher, SIAM Journal on Scientific Computing, 2018. Code.
- Cosmic Divergence, Weak Cosmic Convergence, and Fixed Points at Infinity. E. K. Ryu, Journal of Fixed Point Theory and Applications, 2018.
- Unbalanced and Partial L1 Monge-Kantorovich Problem: A Scalable Parallel First-Order Method. E. K. Ryu, W. Li, P. Yin, and S. Osher, Journal of Scientific Computing, 2018, Slides.
- A Parallel Method for Earth Mover's Distance. W. Li, E. K. Ryu, S. Osher, W. Yin, and W. Gangbo, Journal of Scientific Computing, 2018. Code.
- Convex Optimization for Monte Carlo: Stochastic Optimization for Importance Sampling. E. K. Ryu, Stanford University PhD thesis, Advisor: Stephen P. Boyd, 2016.
- A Primer on Monotone Operator Methods. E. K. Ryu and S. Boyd, Applied and Computational Mathematics, 2016.
- Risk-Constrained Kelly Gambling. E. Busseti, E. K. Ryu, and S. Boyd, Journal of Investing, 2016.
- Extensions of Gauss Quadrature via Linear Programming. E. K. Ryu and S. Boyd, Foundations of Computational Mathematics, 2015.
- Computing Reaction Rates in Bio-molecular Systems Using Discrete Macro-states. E. Darve and E. K. Ryu. In T. Schlick, editor, Innovations in Biomolecular Modeling and Simulations. Royal Society of Chemistry, 2012.
- Structural Characterization of Unsaturated Phosphatidylcholines Using Traveling Wave Ion Mobility Spectrometry. H. Kim, H. Kim, E. Pang, E. K. Ryu, L. Beegle, J. Loo, W. Goddard, and I. Kanik. Analytical Chemistry, 2009.
Workshop papers
- LoRA can Replace Time and Class Embeddings in Diffusion Probabilistic Models. J. Y. Choi, J. Park, I. Park, J. Cho, A. No, and E. K. Ryu, NeurIPS Workshop on Diffusion Models, 2023.
- Diffusion Probabilistic Models Generalize when They Fail to Memorize. T. Yoon, J. Y. Choi, S. Kwon, and E. K. Ryu, ICML Workshop on Structured Probabilistic Inference & Generative Modeling, 2023.