Research



Links:


Scholarly Publications:


    Preprints (Double-blind submissions may not be listed)

  1. Jichao Jiang, Cristian McGee, El Houcine Bergou, HQ Cai, and Aritra Dutta. TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-tuning. arXiv GitHub

  2. HQ Cai, Longxiu Huang, and Juntao You. Quantized Low-Rank Quantum State Tomography: Hyperbolic Quantization and Riemannian Least-Squares Recovery. arXiv

  3. HQ Cai, Longxiu Huang, Jing Qin, and Chengyue Wu. Robust Low-Tubal-Rank Tensor Completion under Cross-Concentrated Sampling. arXiv

  4. Yuan Du, Mitchel Hill, and HQ Cai. Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations. arXiv

  5. Xinyu Chen, HQ Cai, Lijun Ding, and Jinhua Zhao. TailedTS: Benchmark Dataset for Heavy-Tailed Time Series Prediction and Periodicity Quantification. arXiv GitHub

  6. Xinyu Chen, Qi Wang, Yunhan Zheng, Nina Cao, HQ Cai, and Jinhua Zhao. Data-Driven Discovery of Mobility Periodicity for Understanding Urban Systems. arXiv GitHub

  7. Chandra Kundu, Abiy Tasissa, and HQ Cai. A Dual Basis Approach for Structured Robust Euclidean Distance Geometry. arXiv

  8. Akram Heidarizadeh, HQ Cai, George Atia. A Relevance-Guided Approach to Defense-Resistant and Explainable Adversarial Attacks.

  9. Bowen Su, Juntao You, HQ Cai, and Longxiu Huang. Guaranteed Sampling Flexibility for Low-tubal-rank Tensor Completion. arXiv

    10. Journal and Selected Conference Papers

  10. Kai Han, Jin Wang, HQ Cai, Yunhui Shi, Nam Ling, Qingming Huang, and Baocai Yin. MTADUN: Multi-Stage Transmission Augmented Deep Unfolding Network for Task-Adaptable Image Restoration, IEEE Transactions on Image Processing (TIP), to appear.

  11. Chandler Smith, HQ Cai, and Abiy Tasissa. Provable Non-convex Euclidean Distance Matrix Completion: Geometry, Reconstruction, and Robustness, IEEE Transactions on Information Theory (TIT), 72(9): 6993–7011, 2026. arXiv GitHub BibTEX

  12. HQ Cai, Chandra Kundu, Jialin Liu, and Wotao Yin. Deeply Learned Robust Matrix Completion for Large-scale Low-rank Data Recovery, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 48(6): 6541–6556, 2026. arXiv GitHub BibTEX

  13. Akram Heidarizadeh, Akram Awad, HQ Cai, and George Atia. Confidence-guided Self-training for Gradual Domain Adaptation, In International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. GitHub BibTEX Poster

  14. Kai Han, Jin Wang, HQ Cai, Yunhui Shi, Nam Ling, and Baocai Yin. GDU-net: A Cross-gated Dual-domain Optimization Unfolding Network for Image Compressive Sensing, Neurocomputing, 704: 134809, 2026. BibTEX

  15. HQ Cai, Longxiu Huang, Xiliang Lu, and Juntao You. Accelerating Ill-conditioned Hankel Matrix Recovery via Structured Newton-like Descent, Inverse Problems (IP), 41(7): 075015, 2025. arXiv GitHub BibTEX

  16. Xinyu Chen, Dingyi Zhuang, HQ Cai, Shenhao Wang, and Jinhua Zhao. Dynamic Autoregressive Tensor Factorization for Pattern Discovery of Spatiotemporal Systems, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 47(10): 8524–8537, 2025. arXiv BibTEX Poster

  17. Paris Giampouras, HQ Cai, and René Vidal. Guarantees of a Preconditioned Subgradient Algorithm for Overparameterized Asymmetric Low-rank Matrix Recovery, In International Conference on Machine Learning (ICML), 2025. arXiv GitHub BibTEX

  18. Xinyu Chen, HQ Cai, Fuqiang Liu, and Jinhua Zhao. Correlating Time Series with Interpretable Convolutional Kernels, IEEE Transactions on Knowledge and Data Engineering (TKDE), 37(6): 3272–3283, 2025. arXiv GitHub BibTEX

  19. Bumsu Kim, Daniel Mckenzie, HQ Cai, and Wotao Yin. Curvature-Aware Derivative-Free Optimization, Journal of Scientific Computing (JSC), 103(43): 1–28, 2025. arXiv GitHub BibTEX

  20. HQ Cai, Zehan Chao, Longxiu Huang, and Deanna Needell. Robust Tensor CUR Decompositions: Rapid Low-Tucker-Rank Tensor Recovery with Sparse Corruption, SIAM Journal on Imaging Sciences (SIIMS), 17(1): 225–247, 2024. arXiv GitHub BibTEX

  21. Xue Wang, Tian Zhou, Jianqing Zhu, Jialin Liu, Kun Yuan, Tao Yao, Wotao Yin, Rong Jin, and HQ Cai. S3Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching, IEEE Journal of Selected Topics in Signal Processing (JSTSP), 18(6): 985–996, 2024. arXiv GitHub BibTEX

  22. Xinyu Chen, Zhanhong Cheng, HQ Cai, Nicolas Saunier, and Lijun Sun. Laplacian Convolutional Representation for Traffic Time Series Imputation, IEEE Transactions on Knowledge and Data Engineering (TKDE), 36(11): 6490–6502, 2024. arXiv GitHub BibTEX

  23. Kai Han, Jin Wang, Yunhui Shi, HQ Cai, Nam Ling, Baocai Yin. WTDUN: Wavelet Tree-Structured Sampling and Deep Unfolding Network for Image Compressed Sensing, ACM Transactions on Multimedia Computing Communications and Applications (TOMM), 21(1): 33.1–33.22, 2024. arXiv BibTEX

  24. Jialin Liu, Xiaohan Chen, Zhangyang Wang, Wotao Yin, and HQ Cai. Towards Constituting Mathematical Structures for Learning to Optimize, In International Conference on Machine Learning (ICML), 2023. arXiv GitHub BibTEX Poster

  25. HQ Cai, Longxiu Huang, Pengyu Li, and Deanna Needell. Matrix Completion with Cross-Concentrated Sampling: Bridging Uniform Sampling and CUR Sampling, IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 45(8): 10100–10113, 2023. arXiv GitHub BibTEX

  26. HQ Cai, Jian-Feng Cai, and Juntao You. Structured Gradient Descent for Fast Robust Low-Rank Hankel Matrix Completion, SIAM Journal on Scientific Computing (SISC), 45(3): A1172–A1198, 2023. arXiv GitHub BibTEX

  27. HQ Cai, Daniel Mckenzie, Wotao Yin, and Zhenliang Zhang. A One-Bit, Comparison-Based Gradient Estimator, Applied and Computational Harmonic Analysis (ACHA), 60: 242–266, 2022. arXiv GitHub BibTEX

  28. HQ Cai, Daniel Mckenzie, Wotao Yin, and Zhenliang Zhang. Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling, SIAM Journal on Optimization (SIOPT), 32(2): 687–714, 2022. arXiv GitHub BibTEX

  29. HQ Cai, Jialin Liu, and Wotao Yin. Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection. In Advances in Neural Information Processing Systems (NeruIPS), 2021. arXiv GitHub BibTEX Poster

  30. HQ Cai, Yuchen Lou, Daniel Mckenzie, and Wotao Yin. A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization. In International Conference on Machine Learning (ICML), 2021. arXiv GitHub BibTEX Poster

  31. HQ Cai, Keaton Hamm, Longxiu Huang, and Deanna Needell. Mode-wise Tensor Decompositions: Multi-dimensional Generalizations of CUR Decompositions. Journal of Machine Learning Research (JMLR), 22(185): 1–36, 2021. arXiv GitHub BibTEX

  32. HQ Cai, Keaton Hamm, Longxiu Huang, and Deanna Needell. Robust CUR Decomposition: Theory and Imaging Applications. SIAM Journal on Imaging Sciences (SIIMS), 14(4): 1472–1503, 2021. arXiv BibTEX

  33. HQ Cai, Jian-Feng Cai, Tianming Wang, and Guojian Yin. Accelerated Structured Alternating Projections for Robust Spectrally Sparse Signal Recovery. IEEE Transactions on Signal Processing (TSP), 69: 809–821, 2021. arXiv GitHub BibTEX

  34. HQ Cai, Keaton Hamm, Longxiu Huang, Jiaqi Li, and Tao Wang. Rapid Robust Principal Component Analysis: CUR Accelerated Inexact Low Rank Estimation. IEEE Signal Processing Letters (SPL), 28: 116–120, 2020. arXiv GitHub BibTEX

  35. HQ Cai, Jian-Feng Cai, and Ke Wei. Accelerated Alternating Projections for Robust Principal Component Analysis. Journal of Machine Learning Research (JMLR), 20(1): 685–717, 2019. arXiv GitHub BibTEX Poster Demo

    36. Other Referred Conference and Workshop Papers

  36. HQ Cai, Longxiu Huang, Tianming Wang, and Juntao You. Robust Spectral Recovery for Dynamical Sampling. In IEEE International Symposium on Information Theory (ISIT), 2026. arXiv BibTEX

  37. Muhammad Rana, Abiy Tasissa, HQ Cai, Yakov Gavriyelov, and Keaton Hamm. Recovering Wasserstein Distance Matrices from Few Measurements. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2026. arXiv BibTEX

  38. HQ Cai and Longxiu Huang. Property Inheritance for Subtensors in Tensor Train Decompositions. In IEEE International Symposium on Information Theory (ISIT), 2025. arXiv BibTEX

  39. Chandra Kundu, Abiy Tasissa, and HQ Cai. Structured Sampling for Robust Euclidean Distance Geometry. In Conference of Information Sciences and Systems (CISS), 2025. arXiv BibTEX

  40. Akram Heidarizadeh, Connor Hatfield, Lorenzo Lazzarotto, HQ Cai, and George Atia. Explainable Adversarial Attacks on Coarse-to-Fine Classifiers. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025. arXiv BibTEX Poster

  41. Yisen Wang, HQ Cai, and Longxiu Huang. Three-Dimensional Signal Processing: A New Approach in Dynamical Sampling via Tensor Products. In Asilomar Conference on Signals, Systems, and Computers, 2024. arXiv BibTEX

  42. HQ Cai, Longxiu Huang, Chandra Kundu, and Bowen Su. On the Robustness of Cross-Concentrated Sampling for Matrix Completion. In Conference of Information Sciences and Systems (CISS), 2024. arXiv BibTEX

  43. Chandler Smith, Samuel Lichtenberg, HQ Cai, and Abiy Tasissa. Riemannian Optimization for Euclidean Distance Geometry. In Conference on Neural Information Processing Systems (NeurIPS) Workshops, 2023. BibTEX Poster

  44. Zheng Tan, Longxiu Huang, HQ Cai, and Yifei Lou. Non-convex Approaches for Low-Rank Tensor Completion under Tubal Sampling. In International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023. arXiv BibTEX Poster

  45. Keaton Hamm, Mohamed Meskini, and HQ Cai. Riemannian CUR Decompositions for Robust Principal Component Analysis. In International Conference on Machine Learning (ICML) Workshops, 2022. arXiv BibTEX Poster

  46. HQ Cai, Zehan Chao, Longxiu Huang, and Deanna Needell. Fast Robust Tensor Principal Component Analysis via Fiber CUR Decomposition. In International Conference on Computer Vision (ICCV) Workshops, 2021. arXiv GitHub BibTEX

    47. Technical Reports

  47. Dylan King, Caroline Hills, Michael Kielstra, and Matt Torrence. Parallel Time Integration for Constrained Optimization. Lawrence Livermore National Lab, Report No. LLNL-SR-822456, 2020. Sponsoring Mentors: Rob Falgout, Jeff Hittinger, and Cosmin Petra. Academic Mentor: HQ Cai. PDF

  48. Elijah Gross-Sable, Jacky Lee, Xia Li, Tyler Sam, and Nate Sands. Trained to Kill: Analyzing Homicide Data in Los Angeles County. UCLA Computational and Applied Mathematics REU, Final Report for LA Homicide Narratives, 2019. Academic Mentors: Michael Lindstrom and HQ Cai. PDF

Dissertation:


Editorship: