Zobrazeno 1 - 10
of 137
pro vyhledávání: '"Zhu, Zhanxing"'
Autor:
Shen, Qianli, Wang, Yezhen, Yang, Zhouhao, Li, Xiang, Wang, Haonan, Zhang, Yang, Scarlett, Jonathan, Zhu, Zhanxing, Kawaguchi, Kenji
Bi-level optimization (BO) has become a fundamental mathematical framework for addressing hierarchical machine learning problems. As deep learning models continue to grow in size, the demand for scalable bi-level optimization solutions has become inc
Externí odkaz:
http://arxiv.org/abs/2406.14095
Random label noises (or observational noises) widely exist in practical machine learning settings. While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regu
Externí odkaz:
http://arxiv.org/abs/2304.00320
The conventional understanding of adversarial training in generative adversarial networks (GANs) is that the discriminator is trained to estimate a divergence, and the generator learns to minimize this divergence. We argue that despite the fact that
Externí odkaz:
http://arxiv.org/abs/2302.01075
Differentiable physics modeling combines physics models with gradient-based learning to provide model explicability and data efficiency. It has been used to learn dynamics, solve inverse problems and facilitate design, and is at its inception of impa
Externí odkaz:
http://arxiv.org/abs/2202.00504
Publikováno v:
In Artificial Intelligence September 2024 334
Autor:
Zhang, Quanshi, Han, Tian, Fan, Lixin, Zhu, Zhanxing, Su, Hang, Wu, Ying Nian, Ren, Jie, Zhang, Hao
This is the Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI. Deep neural networks (DNNs) have undoubtedly brought great success to a wide range of applications in computer vision, computat
Externí odkaz:
http://arxiv.org/abs/2107.08821
It is well-known that stochastic gradient noise (SGN) acts as implicit regularization for deep learning and is essentially important for both optimization and generalization of deep networks. Some works attempted to artificially simulate SGN by injec
Externí odkaz:
http://arxiv.org/abs/2103.17182
Autor:
Li, Mengzhang, Zhu, Zhanxing
Spatial-temporal data forecasting of traffic flow is a challenging task because of complicated spatial dependencies and dynamical trends of temporal pattern between different roads. Existing frameworks typically utilize given spatial adjacency graph
Externí odkaz:
http://arxiv.org/abs/2012.09641
Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performance. This is known as adversarial attacks. To counter adversarial atta
Externí odkaz:
http://arxiv.org/abs/2012.08112
Autor:
Ji, Guangda, Zhu, Zhanxing
Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation lacks a co
Externí odkaz:
http://arxiv.org/abs/2010.10090