We introduce a lightweight, flexible and end-to-end trainable probability density model parameterized by a constrained Fourier basis. We assess its performance at approximating a range of multi-modal 1D densities, which are generally difficult to fit. In comparison to the deep factorized model introduced in [1], our model achieves a lower cross entropy at a similar computational budget. In addition, we also evaluate our method on a toy compression task, demonstrating its utility in learned compression.
Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting
School of Computing, Macquarie University(麦考瑞大学计算机学院);Department of Automation, Shanghai Jiao Tong University(上海交通大学自动化系);department of Electrical and Electronic Engineering, Hong Kong Polytechnic University(香港理工大学电子与电气工程系)
Narrow Operator Models of Stellarator Equilibria in Fourier Zernike Basis
1 Max-Planck-Institute for Plasma Physics, 17491 Greifswald, Germany 2 Institute for Research in Electronics \& Applied Physics, University of Maryland, MD 20742, USA 3 Mechanical;Aerospace Engineering, Princeton University, NJ 08544, USA
Fourier Sensitivity and Regularization of Computer Vision Models
Institute for Infocomm Research, A*STAR(新加坡科技研究局资讯通信研究院);School of Computing, National University of Singapore(新加坡国立大学计算学院);Institute of Data Science, National University of Singapore(新加坡国立大学数据科学研究所);Centre for Frontier AI Research, A*STAR(新加坡科技研究局前沿人工智能研究中心)
Department of Engineering Management and Systems Engineering(工程管理与系统工程系);Missouri University of Science and Technology(密苏里科技大学);Department of Industrial and Systems Engineering(工业与系统工程系);University of Miami(迈阿密大学)