黄晓霖-上海交通大学自动化与感知学院

研究方向

机器学习

- 核学习方法

- 优化方法（深度学习训练）

- 深度学习的记忆与反学习

- 深度学习的应用

- 分片线性函数的表示、优化、辨识

本页面信息可能滞后，请访问 http://www.pami.sjtu.edu.cn/xiaolin

论文发表情况请参阅谷歌学术

工作经历

2023- 上海交通大学教授

2016-2023 上海交通大学副教授（2023年获长聘教职）

2015-2017 埃尔兰根-纽伦堡大学（Friedrich-Alexander Universität Erlangen-Nürnberg）洪堡学者

2015-2016 鲁汶大学（KU Leuven）自由研究员（兼）

2012-2015 鲁汶大学（KU Leuven）博士后研究员

教育背景

2006-2012 清华大学工学博士（自动化系，系统工程研究所）

2002-2006 西安交通大学工学学士（自动化）/理学学士（数学与应用数学）

教学工作

AU4303 本科生课程《线性规划与非线性规划》

CS2601 本科生课程《线性优化与凸优化》

AU7408 研究生课程《深度学习实战》

ECE4850J (原 VE485) 本科生课程（密歇根学院）《Convex Optimization in Machine Learning》（英文授课）

AU311 本科生课程《模式识别导论》（2017 年至 2025 年）

AU7021 研究生课程《学习与控制中的优化》（2020年至 2024 年）

研究生培养（包含部分巴黎高科、宁波人工智能专项学生）

2016级：杨海岩（硕士研究生，2019 年毕业，入职百度）

2017级：楚天舒（博士研究生，2024 年毕业，入职中国移动研究院）
谢佳轩（硕士研究生，2020年毕业，UC Irvine 攻读博士）
何凡（硕士研究生，2019年毕业，本校攻读博士）

2018级：王凯捷（博士研究生）
孙程锦（硕士研究生，2021年毕业，入职美团）
徐金田（硕士研究生，2021年毕业，入职拼多多）

2019级：吴颖雯（博士研究生，2025年毕业，入职字节跳动）
何凡（博士研究生，2023年毕业，KU Leuven 博士后）
罗钦（硕士研究生，2022年毕业，香港中文大学攻读博士）
姚乐宇（硕士研究生，2022年毕业，入职英特尔）
王鹏博（硕士研究生，2022年毕业，清华大学攻读博士）
谭雷（硕士研究生，2022年毕业，入职字节跳动）

2020级：何铭震（博士研究生，2025年毕业，入职华为中央媒体研究院）
陈思哲（硕士研究生，2023年毕业，UC Berkeley 攻读博士）
李涛（硕士研究生，本校攻读博士）
吴枢同（硕士研究生，2023年毕业，UW-Madison 攻读博士）
李明哲（硕士研究生，2023年毕业，入职字节跳动）
傅雨佳（硕士研究生，2023年毕业，入职字节跳动）
张一航（硕士研究生，2023年毕业，入职国家机关）

2021级：杨睿恺（博士研究生， 2026年毕业，入职腾讯）丁瑞琪（博士研究生）
何正保（硕士研究生，本校攻读博士）
叶之星（硕士研究生，2024年毕业，入职英伟达）
雷泽浩（硕士研究生，2024年毕业，入职中电科研究所）
王天瑶（硕士研究生，2024年毕业，入职国家外汇管理中心）

2022级：黄哲昊（博士研究生）程欣雯（博士研究生）
李涛（博士研究生，2025年毕业，入职字节跳动）

2023级：何正保（博士研究生）
周文杏（硕士研究生，2026年毕业，入职蔚来科技）
田翰凌（硕士研究生，2026年毕业，U-Maryland 攻读博士）

2024级：丘有梅（博士研究生）刘宇航（硕士研究生）章杰（硕士研究生）

2025级：王静颖（博士研究生）张耕毓（硕士研究生）楼苡辛（硕士研究生）

研究成果

代表性论文

[著] S. Boyd, L. Vandenberghe, [译] 王书宁, 许鋆, 黄晓霖: 《凸优化》, 清华大学出版社, 2013.
Z. He, T. Li, X. Cheng, Z. Huang, X. Huang*: Towards Natural Machine Unlearing,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
F. He, R. Yang, L. Shi*, X. Huang*: Decentralized framework for kernel PCA with projection consensus constraints,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025
Y. Wu, T. Li, X. Cheng, J. Yang, X. Huang*: Low-dimensional gradient helps out-of-distribution detection,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
W. Liu*, P. Zhang, H. Qin, X. Huang, J. Yang, M. Ng: Fast image smoothing via quasi weighted least squares,
International Journal of Computer Vision, 2024
K. Fang, Q. Tao, X. Huang*, J. Yang*: Revisiting deep ensemble for out-of-distribution detection: A loss landscape perspective,
International Journal of Computer Vision, 2024
M. He, F. He, L. Shi, X. Huang*, J.A.K. Suykens: Learning with asymmetric kernels: Least squares and feature interpretation,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(8): 10044-10054, 2023
T. Li, L. Tan, Z. Huang, Q. Tao, Y. Liu, X. Huang*: Low Dimensional Trajectory Hypothesis is True: DNNs can be Trained in Tiny Subspaces,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(3): 3411-3412, 2023
Q. Tao*, L. Li*, X. Huang*, X. Xi, S. Wang, J.A.K. Suykens: Piecewise Linear Neural Networks and Deep Learning,
Nature Reviews Methods Primers, 2:42, 2022
F. Liu*, X. Huang*, Y. Chen, J.A.K. Suykens: Towards a Unified Quadrature Framework for Large-Scale Kernel Machines,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(11): 7975-7988, 2022
F. Liu*, X. Huang*, Y. Chen, J.A.K. Suykens: Random Features for Kernel Approximation: A Survey on Algorithms, Theory, and Beyond,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10): 7128-7148, 2022
W. Liu, P. Zhang, Y. Lei, X. Huang*, J. Yang*, M. Ng: A Generalized Framework for Edge-preserving and Structure-preserving Image Smoothing,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(10): 6631-6648, 2022
S. Chen, Z. He, C. Sun, J. Yang, X. Huang*: Universal Adversarial Attack on Attention and the Resulting Dataset DamageNet,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(4): 2188-2197, 2022
S. Tang#, X. Huang#*, M. Chen, C. Sun, J. Yang*: Adversarial Attack Type I: Cheat Classifiers by Significant Changes,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(3): 1100-1109, 2021
F. Liu*, L. Shi, X. Huang, J. Yang*, J.A.K. Suykens: Generalization Properties of Hyper-RKHS and its Applications,
Journal of Machine Learning Research, 22(1): 1-38, 2021
F. Liu, X. Huang*, C. Gong, J. Yang*, L. Li: Learning Data-adaptive Non-parametric Kernels,
Journal of Machine Learning Research, 208: 1-39, 2020
W. Liu, P. Zhang, X. Huang*, J. Yang*, C. Shen, I. Reid: Real-time Image Smoothing via Iterative Least Squares,
ACM Transactions on Graphics, 39(3): 1-10, 2020
L. Shi, X. Huang*, Y. Feng, J.A.K. Suykens: Sparse Kernel Regression with Coefficient-based lq regularization,
Journal of Machine Learning Research, 161:1-64, 2019
X. Huang*, A. Maier, J. Hornegger, J.A.K. Suykens: Indefinite Kernels in Least Squares Support Vector Machine and Principal Component Analysis,
Applied and Computational Harmonic Analysis, 43(1): 162-172, 2017.
Y. Feng*, X. Huang, L. Shi, Y. Yang, J.A.K. Suykens: Learning with the Maximum Correntropy Criterion Induced Losses for Regression,
Journal of Machine Learning Research, 16: 993-1034, 2015.
X. Huang*, L. Shi, J.A.K. Suykens: Ramp Loss Linear Programming Support Vector Machine,
Journal of Machine Learning Research, 15: 2185-2211, 2014.
X. Huang*, L. Shi, J.A.K. Suykens: Support Vector Machine Classifier with Pinball Loss,
IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(5): 984-997, 2014.

其它论文

K. Fang, Q. Tao*, M. He, K. Lv, R. Yang, H. Hu, X. Huang, J. Yang*, L. Cao: Kernel PCA for out-of-distribution detection: Non-linear kernel selection ana approximiation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026.
Z. He, R. Ding, Z. Huang, T. Li, X. Huang*: Compress then merge: From multiple LoRAs into one low-rank adapter, in International Conference on Machine Learning (ICML), 2026
M. Qin, S. Yin, Q. Guo, X. Huang, P. Liu, F. Wen*: Zeroth-order forward-ony SNN training inspiring neuromorphic on-chip learning, in International Conference on Machine Learning (ICML), 2026
Z. Huang, B. Lin, J. Zhang J. Wang, Y. Liu, N. Lu, T. Li, X. Huang*, : VL-RouterBench: A benchmark for vision–language model routing, in Computer Vision and Pattern Recognition (CVPR, Highlight), 2026
Y. Liu, T. Li, Z. Huang, Z. Yang, X. Huang*: Bi-LoRA: Efficient sharpness-aware minimization for fine-tuning large-scale models, in International Conference on Learning Representations (ICLR), 2026
X. Cheng, Z. Huang, W. Zhou, Z. He, R. Yang, Y. Wu, X. Huang*: Remaining-data-free machine unlearning by suppressing sample contribution, in International Conference on Learning Representations (ICLR), 2026
Z. Huang, Y. Liu, B. Lin, Y. Lou, H. Tian, T. Li, X. Huang*: RAIN-Merging: A gradient-free method to enhance instruction following in large reasoning models with preserved thinking format, in International Conference on Learning Representations (ICLR, Oral), 2026
R. Yang, M. He, Z. He, Y. Qiu, X. Huang*: MUSO: Achieving exact machine unlearning in over-parameterized regimes, Machine Learing, 2025
R. Yang, F. He, M. He, J. Yang, X. Huang*: Decentralized kernel ridge regression based on data-dependent random feature, IEEE Transactions on Neural Networks and Learning Systems, 2025
M. He, R. Yang, H. Tian, X. Huang*: Primphormer: Efficient graph transformers with primal representations, in International Conference on Machine Learning (ICML), 2025
T. Li, Z. He, Y. Li, Y. Wang, L. Shang, X. Huang*, Flat-LoRA: Low-rank adaption over a flat loss landscape, in International Conference on Machine Learning (ICML), 2025
H. Tian, Y. Liu, M. He, Z. He, Z. Huang, R. Yang, X. Huang*: Simulating training dynamics to reconstruct training data from deep neural networks, in International Conference on Learning Representations (ICLR), 2025
Y. Wu, R. Yu, X. Cheng, Z. He, X. Huang*: Pursuing feature separation based on neural collapse for out-of-distribution detection, in International Conference on Learning Representations (ICLR), 2025
Z. Huang, X. Cheng, J. Zheng, H. Wang, Z. He, T. Li, X. Huang*: Unified gradient-based machine unlearning with Remain geometry enhancement, in Neural Information Processing Systems (NeurIPS, Spotlight), 2024.
K. Fang, Q. Tao, K. Lv, M. He, X. Huang*, J. Yang*: Kernel PCA for out-of-distribution detection, in Neural Information Processing Sytems (NeurIPS), 2024
M. He, F. He, F. Liu, X. Huang*: Random Fourier features for asymmetric kernels, Machine Learning, 2024
T. Li, W. Jiang, F. Liu, X. Huang*, J. Kwok: Scalable learned model soup on a single GPU: An efficient subspace training strategy, in European Conference on Computer Vision (ECCV), 2024
R. Yang, F. He, J. Yang, X. Huang*: Decentralized kernel ridge regression based on data-dependent random feature, IEEE Transactions on Neural Networks and Learning Systems (NeurIPS), 2024
T. Li, P. Zhou, Z. He, X. Cheng, X. Huang*: Fredenly sharpness-aware minimization, in Computer Vision and Pattern Recognition (CVPR), 2024
X. Geng, J. Wang, J. Gong, Y. Xue, J. Xu*, F. Chen, X. Huang: OrthCaps: An orthogonal CapsNet with sparse attention routing and pruning, in Computer Vision and Pattern Recognition (CVPR), 2024
K. Lv, J. Cai, J. Huo, C. Shang, X. Huang, J. Yang*: Sparse generalized canonical correlation analysis: Distributed alternating iteration based approach, Neural Computation, 2024
M. He, F. He, R. Yang, X. Huang*: Diffusion representation for asymmetric kernels via magnetic transform, Neural Information Processing Systems (NeurIPS), 2023
J. Zhong, X. Huang, X. Yu*: Multi-frame self-supervised depth estimation with multi-scale feature fusion in dynamic senses, ACM International Conference on Multimedia, 2023
Y. Chen, C. Shang, X. Huang, X. Yin*: Data-driven safe controller synthesis for deterministic systems: A posteriori method with validation tests, IEEE Conference on Decision and Control, 2023
T. Chu, Z. Yang, X. Huang*: Improving the post-training neural networks quantization by prepositive feature quantization, IEEE Transactions on Circuits and Systems for Video Technology, 2023
Y. Wu, S. Chen, K. Fang, X. Huang*: Unifying gradients to improve real-world robustness for deep networks, ACM Transactions on Intelligent Systems and Technology, 2023
L. Tan, S. Wu, W. Zhou, X. Huang*: Weighted neural tangent kernel: A generalized and improved network-induced kernel, Machine Learning, 2023.
S. Wu, S. Chen, C. Xie, X. Huang*: One-pixel shortcut: On the learning preference of deep neural networks, in International Conference on Learning Representations (ICLR, Spotlight), 2023.
T. Li, Z. Huang, Q. Tao, Y. Wu, X. Huang*: Trainable weight averaging: Efficient training by optimizing historical solutions, in International Conference on Learning Representations (ICLR), 2023.
S. Chen, G. Yuan, X. Cheng, Y. Gong, M. Qin, Y. Wang, X. Huang*: Self-ensemble protection: Training checkpoints are good data protectors, in International Conference on Learning Representations (ICLR), 2023.
S. Chen, Z. Huang, Q. Tao, X. Huang*: Query attack by multi-identity surrogates, IEEE Transactions on Artificial Intelligence, 2023.
F. He, M. He, L. Shi*, X. Huang*: Global search and analysis for the non-convex two-level l1 penalty, IEEE Transactions on Neural Networks and Learning Systems, 2022.
T. Yan, X. Huang, Q. Zhao*: Hierarchical superpixel segmentation by parallel CRTrees labeling, IEEE Transactions on Image Processing, 2022
Y. Gu*, Y. Xu, X. Huang, J. Yang, W. Xue, G.-Z. Yang: Towards robust histology-prior embedding for endomicroscopy image classification, IEEE Transactions on Medical Imaging, 2022
S. Chen, Z. Huang, Q. Tao, Y. Wu, C. Xie, X. Huang*: Adversarial attack on attackers: Post-process to mitigate black-box score-based query attacks, in Neural Information Processing Systems (NeurIPS), 2022
T. Li, Y. Wu, S. Chen, K. Fang, X. Huang*: Subspace Adversarial Training, in Computer Vision and Pattern Recognition (CVPR, Oral), 2022.
F. Liu#, L. Shi#, X. Huang, J. Yang, J.A.K. Suykens: Analysis of regularized least-squares in reproducing kernel Kreĭn spaces, Machine Learning, 2021
Y. Qin, H. Zheng, Y. Gu, X. Huang, J. Yang*, L. Wang, F. Yao, Y.-M. Zhu, G.-Z. Yang: Learning tubule-sensitive CNNs for pulmonary airway and artery-vein segmentation in CT, IEEE Transactions on Medical Imaging, 2021
S. Chen*, X. Zhong, S. Dorn, N. Ravikumar, Q. Tao, X. Huang, M. Lell, M. Kachelriess, A. Maier: Improving generalization capability of multi-organ segmentation models using dual-energy CT, IEEE Transactions on Radiation and Plasma Medical Sciences, 2021
F. Liu, X. Huang*, L. Shi, J. Yang*, J.A.K. Suykens: A double-variational Bayesian framework in random Fourier features for indefinite kernels, IEEE Transactions on Neural Networks and Learning Systems, 2020
W. Xiao*, X. Huang*, F. He, J. Silva, S. Emrani, A.Chaudhuri: Online robust principal component analysis with change point detection, IEEE Transactions on Multimedia, 2020
C. Ma, C. Gong, X. Li, X. Huang, W. Liu, J. Yang*: Toward making unsupervised graph Hashing discriminative, IEEE Transactions on Multimedia, 22(3): 760-774, 2020.
Y. Qin, J. Wan, H. Zheng, X. Huang, J. Yang*, L. Wu, N. Song, Y. Zhu, G.-Z. Yang: Varifocal-Net: A chromosome classification approach using deep convolutional networks, IEEE Transactions on Medical Imaging, 2019.
F. Liu, X. Huang*, J.Yang*, C. Gong, J.A.K. Suykens: Indefinite kernel logistic regression with concave-inexact-convex procedure, IEEE Transactions on Neural Networks and Learning Systems, 2019
J. Cai, X. Huang*: Modified sparse linear-discriminant analysis via nonconvex penalties, IEEE Transactions on Neural Networks and Learning Systems, 2018
X. Huang*, J.A.K. Suykens, S. Wang, J. Hornegger, A. Maier: Classification with truncated l1 distance kernel, IEEE Transactions on Neural Networks and Learning Systems, 2018.
Y. Huang*, O. Taubmann, X. Huang, V. Haase, G. Lauritsch, A. Maier, Scale-space anisotropic total variation for limited angle tomography, IEEE Transactions on Radiation and Plasma Medical Sciences, 2018.
Y. Lu*, M. Kowarschik, X. Huang, S. Chen, Q. Ren, R. Fahrig, J. Hornegger, A. Maier: Material decomposition using ensemble learning for spectral X-ray imaging, IEEE Transactions on Radiation and Plasma Medical Sciences，2018.
F. Liu, C. Gong, X. Huang, T. Zhou, J. Yang*, D. Tao, Robust visual tracking revisited: From correlation filter to template matching, IEEE Transactions on Image Processing, 2018.
X. Huang*, L. Shi, J.A.K. Suykens: Solution path for pin-SVM classifiers with positive and negative tau value, IEEE Transactions on Neural Networks and Learning Systems, 2017.
Y. Liu*, S. Wu, X. Huang, B. Chen, C. Zhu, Hybrid CS-DMRI: Periodic time-variant subsampling and omnidirectional total variation based reconstruction, IEEE Transactions on Medical Imaging, 2017.
J. Wang*, R. Schaffert, A. Borsdorf, B. Heigl, X. Huang, J. Hornegger, A. Maier: Dynamic 2-D/3-D rigid registration framework using point-to-plane correspondence model, IEEE Transactions on Medical Imaging, 2017.
T. Köhler*, X. Huang, F. Schebesch, A. Aichert, A. Maier, and J. Hornegger: Robust Multi-Frame Super-Resolution Employing Iteratively Re-weighted Minimization, IEEE Transactions on Computational Imaging, 2(1): 42-58, 2016.
Y. Feng*, Y. Yang, X. Huang, S. Mehrkanoon, J.A.K. Suykens: Robust Support Vector Machines for Classification with Non-convex and Smooth Losses, Neural Computation, 28, 1217-1247, 2016.
Y. Yang*, Y. Feng, X. Huang, J.A.K. Suykens: Rank-1 Tensor Properties with Applications to a Class of Tensor Optimization Problems, SIAM Journal on Optimization, 26(1): 171-196, 2016.
C. Shang, F. Yang, X. Gao, X. Huang, J.A.K. Suykens, D. Huang*: Concurrent Monitoring of Operating Condition Deviations and Process Dynamics Anomalies with Slow Feature Analysis, AIChE Journal, 61(11): 3666-3682, 2015.
X. Huang*, L. Shi, J.A.K. Suykens: Asymmetric Least Squares Support Vector Machine, Computational Statistics and Data Analysis, 70: 395-405, 2014.
L. Shi*, X. Huang, J.A.K. Suykens: Quantile Regression with l1-regularization and Gaussian Kernels, Advances in Computational Mathematics, 40(2): 517-551, 2014.
X. Huang*, M. Matijas, J.A.K. Suykens: Hinging Hyperplanes for Time-Series Segmentation, IEEE Transactions on Neural Networks and Learning Systems, 24(8): 1279-1291, 2013.
F. Chen*, X. Huang, J. Zhou: Hierarchical Minutiae Matching for Fingerprint and Palmprint Identification, IEEE Transactions on Image Processing, 22(12): 4964-4971, 2013.
X. Huang, J. Xu, S. Wang*: Exact Penalty and Optimality Condition for Nonseparable Continuous Piecewise Linear Programming, Journal of Optimization Theory and Applications, 155: 145-164, 2012.
X. Huang, J. Xu, X. Mu, S. Wang*: The Hill Detouring Method for Minimizing Hinging Hyperplanes Functions, Computers and Operations Research, 39(7): 1763-1770, 2012.
S. Wang*, X. Huang, Y. Yeung: A Neural Network of Smooth Hinge Functions, IEEE Transactions on Neural Networks, 21(9): 1381-1395, 2010.
J. Xu, X. Huang, S. Wang*: Adaptive Hinging Hyperplanes and its Applications in Dynamic System Identification, Automatica, 45(10):2325-2332, 2009.
S. Wang*, X. Huang, K.K. Junaid: Configuration of Continuous Piecewise Linear Neural Networks, IEEE Transactions on Neural Networks, 19(8): 1431-1445, 2008

荣誉奖励

国家高层次青年人才（2017)
上海交通大学"佳和"优秀青年教师（2024）
上海交通大学"凯原"十佳教师（2024）
高校教师教学创新大赛基础课程（正高组）全国二等奖（2025）、上海市特等奖（2025）、上海交通大学一等奖（2024）

学术任职

Senior Member, IEEE

Editor, Machine Learning

Area Chair, ICLR, ICML, NeurIPS, CVPR, ICCV, AAAI (=sAC)