menu MENU
Qing Qu
1301 Beal AvenueAnn Arbor, MI 48109-2122

Please also see my Google Scholar Profile for the most updated publications.

* indicates equal contribution

Selected Publications

Zhihui Zhu (equal), Tianyu Ding (equal), Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu (2021). A Geometric Analysis of Neural Collapse with Unconstrained Features. (NeurIPS’21, spotlight, top 3%)
Preprint – PDF –  Slides –  BibTex CodeVideo

Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, Zhihui Zhu (2020). Analysis of the Optimization Landscapes for Overcomplete Representation LearningICLR’20oral, top 1.9%.
Preprint – PDF – SlidesBibTex

Qing Qu, Xiao Li, Zhihui Zhu (2019). Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient DescentSIAM Journal on Imaging Science, 13(3): 1630–1652, 2020. (NeurIPS’19spotlight, top 3%).
Preprint – PDF – Code – Poster – SlidesBibTex

Yuqian Zhang, Qing Qu, John Wright (2020). From Symmetry to Geometry: Tractable Nonconvex ProblemsUnder Review at Proceedings of IEEE.
Preprint – PDF –  SlidesBibTex

Ju Sun, Qing Qu, John Wright (2018). A Geometric Analysis of Phase RetrievalFoundations of Computational Mathematics, 18(5):1131–1198, 2018. (ISIT’16).
Preprint – PDF – Code – SlidesBibTex

2024

Can Yaras, Peng Wang, Laura Balzano, Qing Qu (2024). Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation. International Conference on Machine Learning (ICML’24), 2024. (Oral, top 1.5%)
Preprint – PDF –  BibTexCode

Peng Wang, Huikang Liu, Druv Pai, Yaodong Yu, Zhihui Zhu, Qing Qu, Yi Ma (2024). A Global Geometric Analysis of Maximal Coding Rate Reduction. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTex

Huikang Liu*, Peng Wang*, Longxiu Huang, Qing Qu, Laura Balzano (2024). Symmetric Matrix Completion with ReLU Sampling. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTex

Avrajit Ghosh, Xitong Zhang, Kenneth K. Sun, Qing Qu, Saiprasad Ravishankar, Rongrong Wang (2024). Optimal Eye Surgeon: Finding Image Priors Through Sparse Generators at Initialization. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTexCode

Xiang Li, Soo Min Kwon, Ismail R. Alkhouri, Saiprasad Ravishankar, Qing Qu (2024). Decoupled Data Consistency with Diffusion Purification for Image Restoration. ArXiv Preprint arXiv:2403.06054, 2024.
Preprint – PDF –  BibTex

Jiyi Chen*, Pengyu Li*, Yutong Wang, Pei-Cheng Ku, Qing Qu (2024). Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation. ArXiv Preprint arXiv:2403.12354, 2024.
Preprint – PDF –  BibTex

Shijun Liang, Evan Bell, Qing Qu, Rongrong Wang, Saiprasad Ravishankar (2024). Analysis of Deep Image Prior and Exploiting Self-Guidance for Image Reconstruction. ArXiv Preprint arXiv:2402.04097, 2024.
Preprint – PDF –  BibTex

2023

Huijie Zhang*, Yifu Lu*, Ismail Alkhouri, Saiprasad Ravishankar, Dogyoon Song, Qing Qu (2023). Improving Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architectures. Conference on Computer Vision and Pattern Recognition (CVPR’24), 2024.
Preprint – PDF –  BibTex

Soo Min Kwon*, Zekai Zhang*, Dogyoon Song, Laura Balzano, Qing Qu (2023). Efficient Low-Dimensional Compression of Overparameterized Models. Proceedings of The 27th International Conference on Artificial Intelligence and Statistics (AISTATS’24), 2024.
Preprint – PDF –  BibTexCode

Peng Wang*, Xiao Li*, Can Yaras, Zhihui Zhu, Laura Balzano, Wei Hu, Qing Qu (2023). Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination. ArXiv Preprint arXiv:2311.02960, 2023.
Preprint – PDF –  BibTexCode

Pengyu Li*, Yutong Wang*, Xiao Li, Qing Qu (2023). Neural Collapse in Multi-label Learning with Pick-all-label Loss. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTexCode

Jiachen Jiang*, Jinxin Zhou*, Peng Wang, Qing Qu, Dustin Mixon, Chong You*, Zhihui Zhu* (2023). Generalized Neural Collapse for a Large Number of Classes. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTex

Huijie Zhang*, Jinfan Zhou*, Yifu Lu, Minzhe Guo, Liyue Shen, Qing Qu (2023). The Emergence of Reproducibility and Consistency in Diffusion Models. International Conference on Machine Learning (ICML’24), 2024.
Preprint – PDF –  BibTexSlides

Yuexiang Zhai, Shengbang Tong, Xiao Li, Mu Cai, Qing Qu, Yong Jae Lee, Yi Ma (2023). Investigating the Catastrophic Forgetting in Multimodal Large Language Models. Conference on Parsimony and Learning (CPAL’24), 2024.
Preprint – PDF –  BibTex

Ismail Alkhouri*, Shijun Liang*, Rongrong Wang, Qing Qu, Saiprasad Ravishankar (2023). Diffusion-based Adversarial Purification for Robust Deep MRI Reconstruction. ArXiv Preprint arXiv:2309.05794, 2023.
Preprint – PDF –  BibTex

Can Yaras*, Peng Wang*, Wei Hu, Zhihui Zhu, Laura Balzano, Qing Qu (2023). The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks. ArXiv Preprint arXiv:2306.01154, 2023.
Preprint – PDF –  BibTexCodeSlides

Bowen Song*, Soo Min Kwon*, Zecheng Zhang, Xinyu Hu, Qing Qu, Liyue Shen (2023). Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency. The Twelfth International Conference on Learning Representations (ICLR’24), 2024. (spotlight, top 5%)
Preprint – PDF –  BibTex

Evan Bell, Shijun Liang, Qing Qu, Saiprasad Ravishankar (2023). Robust Self-Guided Deep Image Prior. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’23), 2023.
Preprint – PDF –  BibTex

2022

Xiao Li*, Sheng Liu*, Jinxin Zhou, Xinyu Lu, Carlos Fernandez-Granda, Zhihui Zhu, Qing Qu (2022). Understanding and Improving Transfer Learning of Deep Models via Neural Collapse. Transactions on Machine Learning Research (TMLR), 2024.
Preprint – PDF –  BibTex

Can Yaras*, Peng Wang*, Zhihui Zhu, Laura Balzano, Qing Qu (2022). Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian ManifoldNeural Information Processing Systems (NeurIPS’22), 2022.
Preprint – PDF –  BibTexCode

Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu (2022). Are All Losses Created Equal: A Neural Collapse PerspectiveNeural Information Processing Systems (NeurIPS’22), 2022.
Preprint – PDF –  BibTexCode

Tuba Sarwar, Can Yaras, Xiang Li, Qing Qu, Pei-Cheng Ku (2022). Miniaturizing a Chip-Scale Spectrometer Using Local Strain Engineering and Total-Variation Regularized ReconstructionNano Letters 22 (20), 8174-8180, 2022.
Preprint – PDF –  BibTex

Shuo Xie, Jiahao Qiu, Ankita Pasad, Li Du, Qing Qu, Hongyuan Mei (2022). Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer LearningFindings of Empirical Methods in Natural Language Processing (EMNLP), 2022.
Preprint – PDF –  BibTexCode

Sheng Liu, Zhihui Zhu, Qing Qu, Chong You (2022). Robust Training under Label Noise by Over-parameterizationInternational Conference on Machine Learning (ICML’22), 2022.
Preprint – PDF –  BibTexCode

Jinxin Zhou*, Xiao Li*, Tianyu Ding, Chong You, Qing Qu*, Zhihui Zhu* (2022). On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained FeaturesInternational Conference on Machine Learning (ICML’22), 2022.
Preprint – PDF –  BibTexCode

Peng Wang*, Huikang Liu*, Can Yaras*, Laura Balzano, Qing Qu (2022). Linear Convergence Analysis of Neural Collapse with Unconstrained FeaturesOPT 2022: Optimization for Machine Learning (NeurIPS 2022 Workshop), 2022.
Preprint – PDF –  BibTex

2021

Lijun Ding*, Liwei Jiang*, Yudong Chen, Qing Qu, Zhihui Zhu (2021). Rank Overspecified Robust Matrix Recovery: Subgradient Method and Exact RecoveryNeural Information Processing Systems (NeurIPS’21), 2021.
Preprint – PDF –  BibTex

Zhihui Zhu*, Tianyu Ding*, Jinxin Zhou, Xiao Li, Chong You, Jeremias Sulam, Qing Qu (2021). A Geometric Analysis of Neural Collapse with Unconstrained Features. Neural Information Processing Systems (NeurIPS’21), 2021. (spotlight, top 3%)
Preprint – PDF –  Slides –  BibTex Code

Sheng Liu*, Xiao Li*, Yuexiang Zhai, Chong You, Zhihui Zhu, Carlos Fernandez-Granda, Qing Qu (2021). Convolutional Normalization: Improving Deep Convolutional Network Robustness and TrainingNeural Information Processing Systems (NeurIPS’21), 2021.
Preprint – PDF –  BibTex Code

Xiao Li*, Shixiang Chen*, Zengde Deng, Qing Qu, Zhihui Zhu, Anthony Man Cho So (2021). Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type MethodsSIAM Journal on Optimization, 31(3): 1605-1634, 2021.
Preprint – PDF – CodeBibTex

2020

Qing Qu, Yuexiang Zhai, Xiao Li, Yuqian Zhang, and Zhihui Zhu (2020). Geometric Analysis of Nonconvex Optimization Landscapes for Overcomplete LearningInternational Conference on Learning Representations (ICLR’20), 2020. (oral, top 1.9%)
Preprint – PDF – SlidesBibTex

Chong You*, Zhihui Zhu*, Qing Qu, Yi Ma (2020). Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterizationNeural Information Processing Systems (NeurIPS’20), 2020. (spotlight, top 4%)
Preprint – PDF – BibTexCode

Yenson Lau*, Qing Qu*, Han-wen Kuo, Pengcheng Zhou, Yuqian Zhang, and John Wright (2020). Short and Sparse Deconvolution — A Geometric ApproachInternational Conference on Learning Representations (ICLR’20), 2020.
Preprint – PDF – Code – Poster – SlidesWebsite – BibTex

Yuqian Zhang, Qing Qu, John Wright (2020). From Symmetry to Geometry: Tractable Nonconvex ProblemsIn Submission to Proceedings of IEEE.
Preprint – PDF –  SlidesBibTex

Qing Qu*, Zhihui Zhu*, Xiao Li, Manolis C. Tsakiris, John Wright, Rene Vidal (2020). Finding the Sparsest Vectors in a Subspace: Theory, Algorithms, and Applications. In Submission.
Preprint – PDF – SlidesBibTex

2019 & Prior

Qing Qu, Xiao Li, Zhihui Zhu (2019). Exact Recovery of Multichannel Sparse Blind Deconvolution via Gradient DescentSIAM Journal on Imaging Science, 13(3): 1630–1652, 2020. (NeurIPS’19spotlight, top 3%).
Preprint – PDF – Code – Poster – SlidesBibTex

Qing Qu, Yuqian Zhang, Yonina C. Eldar, John Wright (2019). Convolutional Phase Retrieval via Gradient DescentIEEE Trans. on Information Theory, 66(3):1785–1821, Mar. 2020. (NeurIPS’17).
Preprint – PDF – Code – Poster – SlidesBibTex

Ju Sun, Qing Qu, John Wright (2018). A Geometric Analysis of Phase RetrievalFoundations of Computational Mathematics, 18(5):1131–1198, 2018. (ISIT’16).
Preprint – PDF – Code – SlidesBibTex

Ju Sun, Qing Qu, John Wright (2017). Complete Dictionary Recovery over the Sphere I: Overview and the Geometric PictureIEEE Trans. on Information Theory, 63(2): 853 – 884, Feb. 2017. (ICML’15, best student paper award for SPARS’15).
Preprint – PDF – Code – PosterBibTex

Ju Sun, Qing Qu, John Wright (2017). Complete Dictionary Recovery over the Sphere II: Recovery by Riemannian Trust-region MethodIEEE Trans. on Information Theory, 63(2): 853 – 884, Feb. 2017.
Preprint – PDF – Code – PosterBibTex

Qing Qu, Ju Sun, John Wright (2016). Finding a Sparse Vector in a Subspace: Linear Sparsity Using Alternating DirectionsIEEE Trans. on Information Theory, 62(10): 5855 – 5880, Oct. 2016 (NeurIPS’14).
Preprint – PDF – Code – Poster – SlidesBibTex

Qing Qu, Nasser M. Nasrabadi, Trac D. Tran (2015). Subspace Vertex Pursuit: A Fast and Robust Near-Separable Nonnegative Matrix Factorization Method for Hyperspectral UnmixingIEEE Journal of Selected Topics in Signal Processing, 9(6): 1142 – 1155, Sept. 2015. (ICASSP’14)
PDF – PosterBibTex

Ju Sun, Qing Qu, John Wright (2015). When Are Nonconvex Problems Not Scary?NeurIPS’15 Workshop on Nonconvex Optimization for Machine Learning, 2015.
Preprint – PDF –  BibTex

Qing Qu, Nasser M. Nasrabadi, Trac D. Tran (2014). Abundance Estimation for Bilinear Mixture Models via Joint Sparse and Low-Rank RepresentationIEEE Transactions on Geoscience and Remote Sensing, 52(7): 4404 – 4423, Jul. 2014. (ICASSP’13)
PDF – Code – Poster – SlidesBibTex

Xiaoxia Sun, Qing Qu, Nasser M. Nasrabadi, Trac D. Tran (2014). Structured Priors for Sparse-Representation-Based Hyperspectral Image ClassificationIEEE Geoscience and Remote Sensing Letters, 11(7): 1235 – 1239, Jul. 2014.
Preprint – PDFBibTex

Jian Jin, Qing Qu, Yuantao Gu (2013). Robust Zero-point Attraction Least Mean Square Algorithm on Near Sparse System IdentificationIET Signal Processing, 7(3): 210 – 218, May 2013.
Preprint – PDFBibTex