paper-with-me

Papers

Scaling Continuous Kernels with Sparse Fourier Domain Learning

2024-09-15 · Clayton Harper, Luke Wood, Peter Gerstoft, Eric C. Larson

We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often limited by high computational and memory demands. Additionally, these methods are prone to spectral bias, which impedes their ability to capture high-frequency details. To overcome these limitations, we propose a novel approach that leverages sparse learning in the Fourier domain. Our method enables the efficient scaling of continuous kernels, drastically reduces computational and memory requirements, and mitigates spectral bias by exploiting the Gibbs phenomenon.

📄 PDF Abstract BibTeX arXiv:2409.09875

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencySparse Learning

Similar Papers 제목 키워드 기반

Harmonizable mixture kernels with variational Fourier features

2018-10-10 · Zheyang Shen, Markus Heinonen, Samuel Kaski

The expressive power of Gaussian processes depends heavily on the choice of kernel. In this work we propose the novel harmonizable mixture kernel (HMK), a family of expressive, interpretable, non-stationary kernels deriv…

Gaussian Processes

Integrated Variational Fourier Features for Fast Spatial Modelling with Gaussian Processes

2023-08-27 · Talay M Cheema, Carl Edward Rasmussen

Sparse variational approximations are popular methods for scaling up inference and learning in Gaussian processes to larger datasets. For $N$ training points, exact inference has $O(N^3)$ cost; with $M \ll N$ features, s…

Gaussian Processes

Neural Operators with Localized Integral and Differential Kernels

2024-02-26 · Miguel Liu-Schiaffini, Julius Berner, Boris Bonev, Thorsten Kurth 외

Neural operators learn mappings between function spaces, which is practical for learning solution operators of PDEs and other scientific modeling applications. Among them, the Fourier neural operator (FNO) is a popular a…

Operator learning

Scaling Up Computer Vision Neural Networks Using Fast Fourier Transform

2023-02-02 · Siddharth Agrawal

Deep Learning-based Computer Vision field has recently been trying to explore larger kernels for convolution to effectively scale up Convolutional Neural Networks. Simultaneously, new paradigm of models such as Vision Tr…

Stochastic Convolutional Sparse Coding

2019-08-31 · Jinhui Xiong, Peter Richtárik, Wolfgang Heidrich

State-of-the-art methods for Convolutional Sparse Coding usually employ Fourier-domain solvers in order to speed up the convolution operators. However, this approach is not without shortcomings. For example, Fourier-doma…