Wei Huang

According to our database, Wei Huang authored at least 8 papers between 2020 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning.

Wei Huang, Chunrui Liu, Yilan Chen, Tianyu Liu, Richard Yi Da Xu

CoRR, 2022

Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective.

Wei Huang, Yayong Li, Weitao Du, Richard Y. D. Xu, Jie Yin, Ling Chen, Miao Zhang

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Understanding deep learning through ultra-wide neural networks

Wei Huang

PhD thesis, 2021

Gaussian process latent variable model factorization for context-aware recommender systems.

Wei Huang, Richard Yi Da Xu

Pattern Recognit. Lett., 2021

Wide Graph Neural Networks: Aggregation Provably Leads to Exponentially Trainability Loss.

Wei Huang, Yayong Li, Weitao Du, Richard Yi Da Xu, Jie Yin, Ling Chen

CoRR, 2021

On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization.

Wei Huang, Weitao Du, Richard Yi Da Xu

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

2020

Implicit bias of deep linear networks in the large learning rate phase.

Wei Huang, Weitao Du, Richard Yi Da Xu, Chunrui Liu

CoRR, 2020

Mean Field Theory for Deep Dropout Networks: Digging up Gradient Backpropagation Deeply.

Wei Huang, Richard Yi Da Xu, Weitao Du, Yutian Zeng, Yunce Zhao

Proceedings of the ECAI 2020 - 24th European Conference on Artificial Intelligence, 29 August-8 September 2020, Santiago de Compostela, Spain, August 29 - September 8, 2020, 2020