Jongha Jon Ryu

I am a tenure-track Assistant Professor in the Department of Computer Science and Engineering at Penn State, with a joint appointment in the Institute for Computational and Data Sciences. I also hold the Wormley Family Early Career Professorship.

My first name is pronounced Jong-ha (Korean: 종하), but I usually go by Jon.

I develop the mathematical and statistical foundations of scientific machine learning, with the goal of enabling scalable and reliable methods for scientific inference and modeling.

research focus: spectral learning; generative modeling; uncertainty quantification; applications to AI for science.

---

research focus

• neural spectral methods for scalable operator learning
  • NestedLoRA for compact operators [ICML’24a]
  • NestedOMM for positive definite operators [NeurIPS’25b]
  • Koopman analysis via NestedLoRA for dynamical systems [NeurIPS’25a]
• principled methods for probabilistic and generative modeling
  • Score-of-Mixture generative modeling framework [ICML’25a, Spotlight]
  • unified NCE-based lens for energy-based models [ICML’25b]
  • corrected InfoNCE for density-ratio estimation [ICLR’26]
• reliable techniques for uncertainty quantification
  • time-uniform confidence sets for:
    • bounded random variables [TransIT’24]
    • bounded random vectors [ICML’24b, Spotlight]
    • nonnegative random variables [COLT’25] (applied to off-policy contextual bandits)
  • diagnosis of evidential deep learning [NeurIPS’24]

---

bio

Prior to Penn State, I was a postdoc at MIT EECS and RLE, hosted by Gregory W. Wornell. Before MIT, I received my Ph.D. in Electrical Engineering from UC San Diego, advised by Young-Han Kim and Sanjoy Dasgupta, generously supported by the Kwanjeong Educational Foundation. I hold dual B.S. degrees in Electrical and Computer Engineering and Mathematical Sciences, with a minor in Physics, from Seoul National University, graduating with the highest distinction.

[CV] (last updated: 08/17/2026)