Paper citations: [Google Scholar] [Semantic Scholar] [arXiv Personal Page]

Reports

Phase Retrieval: the Role of Overparametrization and a New Method.
    Zhong Zhuang, Yash Travadi, Zhihui Zhu, Ju Sun. In preparation for SIAM Journal on Mathematics of Data Science (SIMODS), 2021.

Early Stopping beyond Supervised Learning: Self-Validation.
    Taihui Li, Zhong Zhuang, Hengyue Liang, Le Peng, Hengkang Wang, Ju Sun. Submitted to British Machine Vision Conference (BMVC), Jun 2021.

Phase Retrieval using Single-Instance Deep Generative Prior. [arXiv]
    Kshitij Tayal, Raunak Manekar, Zhong Zhuang, David Yang, Vipin Kumar, Felix Hofmann, Ju Sun. Jun 2021.

A Prospective Observational Study to Investigate Performance of a Chest X-ray Artificial Intelligence Diagnostic Support Tool Across 12 U.S. Hospitals. [medRxiv] [arXiv]
    Ju Sun, Le Peng, Taihui Li, Dyah Adila, Zach Zaiman, Genevieve B. Melton, Nicholas Ingraham, Eric Murray, Daniel Boley, Sean Switzer, John L. Burns, Kun Huang, Tadashi Allen, Scott D. Steenburg, Judy Wawira Gichoya, Erich Kummerfeld, Christopher Tignanelli. Submitted to JAMA, Jun 2021.

Towards Low-Photon Nanoscale Imaging: Holographic Phase Retrieval via Maximum Likelihood Optimization. [arXiv]
    David A. Barmherzig, Ju Sun. May 2021.

Rethink Transfer Learning in Medical Image Classification. [arXiv] [Project website]
    Le Peng, Hengyue Liang, Taihui Li, Ju Sun. Submitted to International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Mar 2021.

Inverse Problems, Deep Learning, and Symmetry Breaking. [arXiv]
    Kshitij Tayal, Chieh-Hsin Lai, Vipin Kumar, Ju Sun. Mar 2020.

Dual-Reference Design for Holographic Coherent Diffraction Imaging. [arXiv]
    David Barmherzig, Ju Sun, Po-Nan Li, TJ Lane, and Emmanuel J. Candès. Feb 2019.

Subgradient Descent Learns Orthogonal Dictionaries. [arXiv]
    Yu Bai, Qijia Jiang, Ju Sun. 2018.

Journals

Potential and Limitations of Radiomics in Neuro-oncology. [Paper]
    Birra Taha, Daniel Boley, Ju Sun, Clark C. Chen. Journal of Clinical Neuroscience, 90:206–211, 2021.

State of Radiomics in Glioblastoma. [Paper]
    Birra Taha, Daniel Boley, Ju Sun, Clark C. Chen. Neurosurgery, 2021. Accepted.

Detection of Isocitrate Dehydrogenase Mutated Glioblastomas through Anomaly Detection Analytics. [Paper]
    Birra Taha, Taihui Li, Daniel Boley, Clark C. Chen, Ju Sun. Neurosurgery, 2021. Accepted.

Dictionary Learning in Fourier Transform Scanning Tunneling Spectroscopy. [arXiv] [Paper]
    Sky Cheung, John Shin, Yenson Lau, Zhengyu Chen, Ju Sun, Yuqian Zhang, John Wright, and Abhay Pasupathy. Nature Communications, 11, 1081, 2020.

Holographic Phase Retrieval and Reference Design. [arXiv] [Paper]
    David Barmherzig, Ju Sun, Po-Nan Li, TJ Lane, and Emmanuel J. Candès. Inverse Problems, 35(9):094001, 2019.

High-Speed Channel Modeling with Machine Learning Methods for Signal Integrity Analysis. [Draft][Paper]
    Tianjian Lu, Ju Sun, Ken Wu, Zhiping Yang. IEEE Trans. Electromagnetic Compatibility, 60(6):1957–1964, 2018.

A Geometrical Analysis of Phase Retrieval. [extended abstract][arXiv] [Paper]
    Ju Sun, Qing Qu, John Wright. Foundations of Computational Mathematics, 18(5):1131–1198, 2018.

Complete Dictionary Recovery over the Sphere I: Overview and the Geometric Picture. [summary][Arxiv] [Paper][Codes][Arxiv-Full Report]
    Ju Sun, Qing Qu, John Wright. IEEE Trans. Information Theory, 63(2): 853 - 884, 2017.

Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region Method. [summary][Arxiv] [Paper] [Codes][Arxiv-Full Report]
    Ju Sun, Qing Qu, John Wright. IEEE Trans. Information Theory, 63(2): 885 – 914, 2017.

Finding a Sparse Vector in a Subspace: Linear Sparsity Using Alternating Direction. [arXiv] [Paper] [Codes]
    Qing Qu, Ju Sun, John Wright. IEEE Trans. Information Theory, 62(10): 5855 - 5880, 2016.

Efficient Point-to-Subspace Query in $\ell^1$ with Application to Robust Object Instance Recognition. [arXiv] [paper]
    Ju Sun, Yuqian Zhang, John Wright. SIAM J. Imaging Sciences (SIIMS), 7(4):2105 - 2138, 2014.

Robust Recovery of Subspace Structures by Low-Rank Representation. [arXiv] [paper] [Codes1]
    Guangcan Liu, Zhouchen Lin, Shuicheng Yan, Ju Sun, Yong Yu, and Yi Ma. IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), 35(1):171 - 184, 2013.

Conferences and Workshops

Unlocking Inverse Problems Using Deep Learning: Breaking Symmetries in Phase Retrieval. [paper] [poster]
    Kshitij Tayal, Chieh-Hsin Lai, Raunak Manekar, Zhong Zhuang, Vipin Kumar, Ju Sun. NeurIPS 2020 Workshop on Deep Learning and Inverse Problems, 2020.

Deep Learning Initialized Phase Retrieval. [paper] [poster]
    Raunak Manekar, Zhong Zhuang, Kshitij Tayal, Vipin Kumar, Ju Sun. NeurIPS 2020 Workshop on Deep Learning and Inverse Problems, 2020.

Rethink Autoencoders: Robust Manifold Learning. [paper]
    Taihui Li, Rishabh Mehta, Zecheng Qian, Ju Sun. ICML workshop on Uncertainty and Robustness in Deep Learning, 2020.

Phase Retrieval via Second-Order Nonsmooth Optimization. [paper]
    Zhong Zhuang, Gang Wang, Yash Travadi, Ju Sun. ICML workshop on Beyond First Order Methods in Machine Learning, 2020.

End-to-End Learning for Phase Retrieval. [paper]
    Raunak Manekar, Kshitij Tayal, Vipin Kumar, Ju Sun. ICML workshop on ML Interpretability for Scientific Discovery, 2020.

Inverse Problems, Deep Learning, and Symmetry Breaking. [paper]
    Kshitij Tayal, Chieh-Hsin Lai, Raunak Manekar, Vipin Kumar, Ju Sun. ICML workshop on ML Interpretability for Scientific Discovery, 2020.

Low-Photon Holographic Phase Retrieval. [paper]
    David A. Barmherzig, Ju Sun. OSA Imaging and Applied Optics Congress 2020.

Dual-Reference Design for Holographic Phase Retrieval. [arXiv] [Paper]
    David Barmherzig, Ju Sun, Emmanuel J. Candès, TJ Lane, and Po-Nan Li. International Conference on Sampling Theory and Application (SampTA), 2019.

Subgradient Descent Learns Orthogonal Dictionaries. [Paper] [arXiv]
    Yu Bai, Qijia Jiang, Ju Sun. International Conference on Learning Representations (ICLR), 2019.

When Nonsmoothness Meets Nonconvexity.
    Yu Bai, Qijia Jiang, Ju Sun, Emmanuel Candès.

  • Invited talk at Allerton Conference on Communication, Control, and Computing 2018. [Slides]

1D Phase Retrieval and Spectral Factorization. [draft] [paper] [slides]
    David A. Barmherzig, Ju Sun. OSA Imaging and Applied Optics Congress 2018.

On Block-Reference Coherent Diffraction Imaging. [draft] [paper] [slides]
    David A. Barmherzig, Ju Sun, T.J. Lane, and Po-Nan Li. OSA Imaging and Applied Optics Congress 2018.

A Local Analysis of Block Coordinate Descent for Gaussian Phase Retrieval. [arXiv][Codes]
    David Barmherzig, Ju Sun. NIPS Workshop on Optimization for Machine Learning, 2017.

A Geometrical Analysis of Phase Retrieval. [extended abstract][arXiv]
    Ju Sun, Qing Qu, John Wright. International Symposium on Information Theory (ISIT), 2016.

When Are Nonconvex Problems Not Scary?. [arXiv] [poster]
    Ju Sun, Qing Qu, John Wright. NIPS Workshop on Non-convex Optimization for Machine Learning: Theory and Practice, 2015.

Complete Dictionary Recovery over the Sphere. [summary] [Extended Abstract] [Arxiv]
    Ju Sun, Qing Qu, John Wright.

  • Short Abstract in International Conference on Sampling Theory and Applications (SampTA), 2015.
  • Short Abstract in Workshop on Signal Processing with Adaptive Sparse Structured Representations (SPARS) [Best Student Paper Award], 2015.
  • Extended Abstract in International Conference on Machine Learning (ICML), 2015.

Finding a Sparse Vector in a Subspace: Linear Sparsity Using Alternating Direction. [arXiv] [paper] [poster] [Codes]
    Qing Qu, Ju Sun, John Wright. Advances in Neural Information Processing Systems (NIPS), 2014.

Efficient Point-to-Subspace Query in $\ell^1$: Theory and Applications in Computer Vision [arXiv].
    Ju Sun, Yuqian Zhang, John Wright. NIPS Workshop on Big Learning, 2012.

Efficient Point-to-Subspace Query in $\ell^1$ with Application to Robust Face Recognition.[arXiv][Poster][Video Highlight]
    Ju Sun, Yuqian Zhang, John Wright. European Conference on Computer Vision (ECCV), 2012.

Closed-Form Solutions to a Category of Nuclear Norm Minimization Problems. [arXiv]
    Guangcan Liu, Ju Sun, Shuicheng Yan. NIPS Workshop on Low-Rank Methods for Large-Scale Machine Learning, 2010.

Robust Low-Rank Subspace Segmentation with Semi-Definite Guarantees. [arXiv] [Slides]
    Yuzhao Ni, Ju Sun, Xiaotong Yuan, Shuicheng Yan, Loong-Fah Cheong. ICDM Workshop on Optimization Based Methods for Emerging Data Mining Problems (OEDM), 2010.

Randomized Locality Sensitive Vocabularies for Bag-of-Features Model. [PDF]
    Yadong Mu, Ju Sun, Shuicheng Yan, Loong-Fah Cheong. European Conference on Computer Vision (ECCV), 2010.

Activity Recognition Using Dense Long-Duration Trajectories. [PDF] [Slides]
    Ju Sun, Yadong Mu, Shuicheng Yan, Loong-Fah Cheong. International Conference on Multimedia & Expo (ICME), 2010 (Invited paper to special session).

Hierarchical Spatio-Temporal Context Modeling for Action Recognition. [PDF]
    Ju Sun, Xiao Wu, Shuicheng Yan, Loong-Fah Cheong, Tat-Seng Chua, Jintao Li. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2009 (Oral).

3D Ordinal Constraint in Spatial Configuration for Robust Scene Recognition. [PDF]
    Ching-Lik Teo, Shimiao Li, Loong-Fah Cheong, Ju Sun. IEEE International Conference on Pattern Recognition (ICPR), 2008.

Dissertation

When Are Nonconvex Optimization Problems Not Scary? [PDF] [Official Version]

Unpublished Reports

Selective Image Super-Resolution. [arXiv]
    Ju Sun, Qiang Chen, Shuicheng Yan, Loong-Fah Cheong. Mar 2010.

  1. Code maintained by Dr. Guangcan Liu