Jongha Jon Ryu
Postdoctoral Associate at MIT
Room 36-677
50 Vassar St
Cambridge, MA 02139
I am currently a postdoctoral associate at MIT, hosted by Gregory W. Wornell. Prior to joining MIT, I received my Ph.D. in Electrical Engineering from UC San Diego, where I was fortunate to be advised by Young-Han Kim and Sanjoy Dasgupta. My graduate study was generously supported by the Kwanjeong Educational Foundation. Before the graduate study, I received my B.S. in Electrical and Computer Engineering and B.S. in Mathematical Sciences (with minor in Physics) with the highest distinction from Seoul National University in 2015.
In general, I aim to develop fundamental yet practical algorithms for machine learning and data science.
My recent research topics include:
- neural-net-based methods for large-scale spectral decomposition problems [NeuralSVD];
- representation learning [NeuralSVD; WynerVAE; kernel embedding without EVD];
- sequential decision making / online learning
- universal-gambling-based confidence sequences [1],[2];
- universal-gambling-based parameter-free online learning;
- learning with uncertainty [where is the success of evidential deep learning coming from?].
As an information theorist by training, I enjoy doing research by simplifying intricate ideas, unifying concepts, and generalizing them to address complex problems.
Check out my resume for more information.
news
Feb 23, 2024 | I gave a talk on our recent work NeuralSVD at ITA workshop! |
---|---|
Feb 10, 2024 | Three preprints about (1) how to perform SVD using neural networks, (2) how to improve uncertainty quantification in deep learning, and (3) how to construct time-uniform confidence sets for bounded vector-valued processes using gambling have been posted on arXiv. Please reach out if you have any comments or questions on any of these! |
Dec 14, 2023 | I will present a poster on decomposing linear operators with neural networks at ML4PS Workshop @NeurIPS 2023. The extended abstract can be found here. The full paper with code will be made available online soon! |
Nov 03, 2023 | I presented my recent work on decomposing linear operators with neural networks at MLTea talk. |
selected publications
- arXivLearning with Succinct Common Representation with Wyner’s Common InformationFebruary 2022arXiv:1905.10945v2
A preliminary version of this manuscript was presented at the Bayesian Deep Learning Workshop at NeurIPS 2018, and an abridged version of the current manuscript was presented at the Bayesian Deep Learning workshop at NeurIPS 2021. - arXivOperator SVD with Neural Networks via Nested Low-Rank ApproximationFebruary 2024arXiv:2402.03655
An extended abstract was presented at Machine Learning and the Physical Sciences Workshop, NeurIPS 2023.