· 智源学者

博士,1987年2月出生,北京大学数据科学研究中心特聘研究员。2016年在英国爱丁堡大学获得机器学习方向博士学位。主要研究领域为人工智能,机器学习,深度学习,强化学习,大规模优化及贝叶斯计算,以及机器学习在安全、图形学、交通大数据中的应用等。在人工智能/机器学习领域顶级期刊及会议有30多篇文章发表,包括NIPS, ICML, CVPR, ACL, IJCAI, AAAI及ECML 等。曾获得计算机安全领域旗舰会议CCS 2018的最佳论文提名。

代表性成果

在深度学习的前沿理论和算法方面有长期积累,集中研究深度学习的工作机制和理论问题,并基于此研究如何提高改进深度学习的算法。持续在AI领域的顶级会议NIPS,ICML及CVPR上多篇文章发表。代表作如下:

  1. Bing Yu, Jingfeng Wu, Jinwen Ma and Zhanxing Zhu*. “Tangent-Normal Adversarial Regularization for Semi-supervised Learning”. The 30th IEEE Conference on Computer Vision and Pattern Recognition. (CVPR 2019, Oral Presentation)
  2. Ju Xu, Zhanxing Zhu*. “Reinforced Continue Learning”. 32nd Annual Conference on Neural Information Processing Systems (NIPS 2018).
  3. Nanyang Ye, Zhanxing Zhu*. “Bayesian Adversarial Learning”. 32nd Annual Conference on Neural Information Processing Systems (NIPS 2018).
  4. Rui Luo, Yaodong Yang, Jianhong Wang, Zhanxing Zhu*, Jun Wang*. “Thermostat-assisted continuously- tempered Hamiltonian Monte Carlo for Bayesian learning”. 32nd Annual Conference on Neural Information Processing Systems (NIPS 2018)
  5. Nanyang Ye, Zhanxing Zhu*, Rafal K. Mantiuk. “Langevin Dynamics with Continuous Tempering for Training Deep Neural Networks”. In 31st Annual Conference on Neural Information Processing Systems(NIPS 2017).
  6. Lei Wu, Zhanxing Zhu*and Weinan E. “Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes”. 34th International Conference on Machine Learning. (ICML 2017 Workshop)
  7. Zhanxing Zhu#, Xiaocheng Shang#, Bendict Leimkuhler, and Amos Storkey. “Covariance-Controlled Adaptive Langevin Thermostat for Large-scale Bayesian Sampling”. In Annual Conference on Neural Information Processing Systems (NIPS 2015).

拟研究项目名称:深度学习的理论理解与分析

All Posts
×

Almost done…

We just sent you an email. Please click the link in the email to confirm your subscription!

OK