We propose a deep supervised learning algorithm based on low-discrepancy sequences as the training set. By a combination of theoretical arguments and extensive numerical experiments we demonstrate that the proposed algorithm significantly outperforms standard deep learning algorithms that are based on randomly chosen training data, for problems in moderately high dimensions. The proposed algorithm provides an efficient method for building inexpensive surrogates for many underlying maps in the context of scientific computing.
Quasi-Monte Carlo Feature Maps for Shift-Invariant Kernels
IBM T.J. Watson Research Center(IBM托马斯·J·沃森研究中心);Google Research(谷歌研究院);Stanford University(斯坦福大学);International Computer Science Institute(国际计算机科学研究所);University of California at Berkeley(加州大学伯克利分校)
Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation
Shanghai AI Laboratory(上海人工智能实验室);Mila, Université de Montréal(蒙特利尔大学米拉研究所);Zelixir Biotech(泽列西尔生物科技公司);Fudan University(复旦大学);The Chinese University of Hong Kong(香港中文大学)
Enhancing Recommendation with Denoising Auxiliary Task
College of Big Data and information engineering, Guizhou University(贵州大学大数据与信息工程学院);Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所);University of the Chinese Academy of Sciences(中国科学院大学)
EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
Department of Computer Science, National Tsing Hua University(国立清华大学计算机科学系);Department of Computer Science, National Taiwan University(国立台湾大学计算机科学系);NVIDIA AI Technology Center (NVAITC), NVIDIA Corporation(NVIDIA人工智能技术中心)