徐易，博士，教授，博士生导师，入选国家级青年人才计划。毕业于美国爱荷华大学(The Unversity of Iowa)计算机科学系，获计算机科学专业博士学位，导师是Prof. Tianbao Yang和Prof. Qihang Lin。硕士毕业于美国南达科他州立大学，本科毕业于浙江大学数学系。加入大连理工大学之前，曾任阿里巴巴达摩院算法专家。

主要研究方向为机器学习、机器视觉、数据驱动的人工智能、统计学习理论、优化。

课题组常年招收学生，欢迎对人工智能具有浓厚兴趣的学生联系我(yxu AT dlut DOT edu DOT cn)，组内经费充足，资源丰富。 推免/考研招生专业为 人工智能（电子信息与电气工程学部）；招收2024年秋季入学博士生（电子信息与电气工程学部 人工智能 专业）。长期招收本科实习生、博士后。

发表论文： (全部论文见谷歌学术：https://scholar.google.com/citations?user=D4jEMqEAAAAJ&hl=en)

• Yang Yang, Yuxuan Zhang, Xin Song, Yi Xu. Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning. Accepted to NeurIPS 2023. (CCF A)

• Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji. Supported Value Regularization for Offline Reinforcement Learning. Accepted to NeurIPS 2023. (CCF A)

• Yixiu Mao, Hongchang Zhang, Chen Chen, Yi Xu, Xiangyang Ji. Supported Trust Region Optimization for Offline Reinforcement Learning. ICML 2023. (CCF A)

• Ziquan Liu, Yi Xu#, Xiangyang Ji, Antoni Chan. TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization. CVPR 2023. (CCF A)

• Hongchang Zhang, Yixiu Mao, Boyuan Wang, Shuncheng He, Yi Xu, Xiangyang Ji. In-sample Actor Critic for Offline Reinforcement Learning. ICLR 2023. 

• Ziquan Liu, Yi Xu#, Yuanhong Xu, Qi Qian, Hao Li, Xiangyang Ji, Antoni Chan, Rong Jin. Improved Fine-Tuning by Better Leveraging Pre-Training Data. NeurIPS 2022. (CCF A)

• Zhiwu Qing, Shiwei Zhang, Ziyuan Huang, Yi Xu, Xiang Wang, Mingqian Tang, Changxin Gao, Rong Jin, Nong Sang. Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency. CVPR 2022. (CCF A)

• Zejiang Hou, Minghai Qin, Fei Sun, Xiaolong Ma, Kun Yuan, Yi Xu, Yen-Kuang Chen, Rong Jin, Yuan Xie, Sun-Yuan Kung. CHEX: CHannel EXploration for CNN Model Compression. CVPR 2022. (CCF A)

• Xiaolong Ma, Minghai Qin, Fei Sun, Zejiang Hou, Kun Yuan, Yi Xu, Yanzhi Wang, Yen-Kuang Chen, Rong Jin, and Yuan Xie. Effective Model Sparsification by Scheduled Grow-and-Prune Methods. ICLR 2022.

• Qi Qi, Zhishuai Guo, Yi Xu, Rong Jin, Tianbao Yang. An Online Method for A Class of Distributionally Robust Optimization with Non-convex Objectives. NeurIPS 2021. (CCF A)

• Yi Xu, Lei Shang, Jinxing Ye, Qi Qian, Yu-Feng Li, Baigui Sun, Hao Li, Rong Jin. Dash: Semi-Supervised Learning with Dynamic Thresholding. ICML 2021. (Long Talk, acceptance rate: 3%) (CCF A)

• Zhuoning Yuan*, Zhishuai Guo*, Yi Xu, Yiming Ying, Tianbao Yang. (*equal contribution) Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity. ICML 2021. (CCF A)

• Yan Yan, Yi Xu, Qihang Lin, Wei Liu, Tianbao Yang. Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization. NeurIPS 2020. (CCF A)

• Yan Yan, Yi Xu, Lijun Zhang, Xiaoyu Wang, Tianbao Yang. Stochastic Optimization for Non-convex Inf-Projection Problems. ICML 2020. (CCF A)

• Yi Xu, Shenghuo Zhu, Sen Yang, Chi Zhang, Rong Jin, Tianbao Yang. Learning with Non-Convex Truncated Losses by SGD. UAI 2020. (CCF B)

• Yi Xu, Rong Jin, Tianbao Yang. Non-asymptotic Analysis of Stoc hastic Methods for Non-Smooth Non-Convex Regularized Problems. NeurIPS 2019. (CCF A)

• Yi Xu, Zhuoning Yuan, Sen Yang, Rong Jin, Tianbao Yang. On the Convergence of (Stochastic) Gradient Descent with Extrapolation for Non-Convex Minimization. IJCAI 2019. (CCF A)

• Yi Xu, Qi Qi, Qihang Lin, Rong Jin, Tianbao Yang. Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Nonasymptotic Convergence. ICML 2019. (CCF A)

• Zaiyi Chen, Yi Xu, Haoyuan Hu, Tianbao Yang. Katalyst: Boosting Convex Katayusha for Non-Convex Problems with a Large Condition Number. ICML 2019. (CCF A)

• Yi Xu, Rong Jin, Tianbao Yang. First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time. NeurIPS 2018. (CCF A)

• Zaiyi Chen*, Yi Xu*, Enhong Chen, Tianbao Yang. (*equal contribution) SadaGrad: Strongly Adaptive Stochastic Gradient Methods. ICML 2018. (CCF A)

• Yi Xu, Qihang Lin, Tianbao Yang. Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter. NeurIPS 2017. (CCF A)

• Yi Xu, Mingrui Liu, Qihang Lin, Tianbao Yang. ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization. NeurIPS 2017. (CCF A)

• Yi Xu, Qihang Lin, Tianbao Yang. Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence. ICML 2017. (CCF A)

• Yi Xu, Haiqing Yang, Lijun Zhang, Tianbao Yang. Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee. AAAI 2017. (CCF A)

• Yi Xu*, Yan Yan*, Qihang Lin, Tianbao Yang. (*equal contribution) Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than O(1/ϵ). NeurIPS 2016. (CCF A)

• Zhiwu Qing, Shiwei Zhang, Ziyuan Huang, Yi Xu, Xiang Wang, Mingqian Tang, Changxin Gao, Rong Jin, Nong Sang. Self-Supervised Learning from Untrimmed Videos via Hierarchical Consistency. Accepted to TPAMI 2023. (CCF A)

• Qi Qi, Yi Xu, Rong Jin, Wotao Yin, Tianbao Yang. Attentional Biased Stochastic Gradient Descent. Accepted to TMLR 2023.

• Yi Xu, Qihang Lin, Tianbao Yang. Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition. Analysis and Applications. Vol. 17, No. 05, pp. 773-818, 2019