no code implementations • CVPR 2016 • Xianglong Liu, Xinjie Fan, Cheng Deng, Zhujin Li, Hao Su, DaCheng Tao
Despite its successful progress in classic point-to-point search, there are few studies regarding point-to-hyperplane search, which has strong practical capabilities of scaling up in many applications like active learning with SVMs.
no code implementations • 17 Oct 2019 • Xinjie Fan, Yuguang Yue, Purnamrita Sarkar, Y. X. Rachel Wang
In this paper, we provide a framework with provable guarantees for selecting hyperparameters in a number of distinct models.
1 code implementation • ICLR 2020 • Xinjie Fan, Yizhe Zhang, Zhendong Wang, Mingyuan Zhou
To stabilize this method, we adapt to contextual generation of categorical sequences a policy gradient estimator, which evaluates a set of correlated Monte Carlo (MC) rollouts for variance control.
no code implementations • 29 Sep 2020 • Nan Ding, Xinjie Fan, Zhenzhong Lan, Dale Schuurmans, Radu Soricut
Models based on the Transformer architecture have achieved better accuracy than the ones based on competing architectures for a large set of tasks.
1 code implementation • NeurIPS 2020 • Xinjie Fan, Shujian Zhang, Bo Chen, Mingyuan Zhou
Attention modules, as simple and effective tools, have not only enabled deep neural networks to achieve state-of-the-art results in many domains, but also enhanced their interpretability.
1 code implementation • ICLR 2021 • Xinjie Fan, Shujian Zhang, Korawat Tanwisuth, Xiaoning Qian, Mingyuan Zhou
However, the quality of uncertainty estimation is highly dependent on the dropout probabilities.
no code implementations • CVPR 2021 • Xinjie Fan, Qifei Wang, Junjie Ke, Feng Yang, Boqing Gong, Mingyuan Zhou
As a generic tool, the improvement introduced by ASR-Norm is agnostic to the choice of ADA methods.
no code implementations • 9 Jun 2021 • Shujian Zhang, Xinjie Fan, Bo Chen, Mingyuan Zhou
Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks.
1 code implementation • NeurIPS 2021 • Korawat Tanwisuth, Xinjie Fan, Huangjie Zheng, Shujian Zhang, Hao Zhang, Bo Chen, Mingyuan Zhou
Existing methods for unsupervised domain adaptation often rely on minimizing some statistical distance between the source and target samples in the latent space.
1 code implementation • NeurIPS 2021 • Shujian Zhang, Xinjie Fan, Huangjie Zheng, Korawat Tanwisuth, Mingyuan Zhou
The neural attention mechanism has been incorporated into deep neural networks to achieve state-of-the-art performance in various domains.
no code implementations • ICML 2020 • Xinjie Fan, Yuguang Yue, Purnamrita Sarkar, Y. X. Rachel Wang
Tuning hyperparameters for unsupervised learning problems is difficult in general due to the lack of ground truth for validation.