* indicates co-first authors
See full list of publications: Publications, Google Scholar
J. Yi*, J. Gao*, T. Wang, X. Wu, W. Xu. Outlier detection using generative models with theoretical performance guarantees. IEEE transactions on information theory (to appear). pdf
J. Yi, S. Dasgupta, JF. Cai, M. Jacob, J. Gao, M. Cho, W. Xu. Separation-free super-resolution from compressed measurements is possible: an orthonormal atomic norm minimization approach. Information and Inference: A Journal of the IMA 12(3):2351-405, 2023. pdf
J. Yi, Q. Zhang, Z. Chen, Q. Liu, W. Shao, Y. He, Y. Wang. Mutual information learned regressor: an information-theoretic viewpoint of training regression systems. arXiv preprint arXiv:2211.12685 (2022). pdf
J. Yi, Q. Zhang, Z. Chen, Q. Liu, and W. Shao. Mutual information learned classifiers: an information-theoretic viewpoint of training deep learning classification systems. arXiv preprint arXiv:2210.01000 (2022). pdf
J. Yi, R. Mudumbai, and W. Xu. Derivation of information-theoretically optimal adversarial attacks with applications to robust machine learning, arXiv preprint arXiv:2007.14042 (2020). pdf
J. Yi, W. Xu. Necessary and sufficient null space condition for nuclear norm minimization in low-rank matrix recovery. IEEE Transactions on Information Theory 66(10): 6597-6604, 2020. pdf
J. Yi, H. Xie, L. Zhou, X. Wu, W. Xu, and R. Mudumbai. Trust but verify: an information-theoretical explanation for the adversarial fragility of machine learning systems, and a general defense against adversarial attacks, arXiv preprint arXiv:1905.11381 (2019). pdf