272 citations · 298 across the 11 of their papers we have counts for
12 papers
ABMB: Deep Delensing Assisted Likelihood-Free Inference from CMB Polarization Maps
Kai Yi, Yanan Fan, Jan Hamann +2
The existence of a cosmic background of primordial gravitational waves (PGWB) is a robust prediction of inflationary cosmology, but it has so far evaded discovery. The most promisi…
Approximate Equivariance SO(3) Needlet Convolution
Kai Yi, Jialin Chen, Yu Guang Wang +4
This paper develops a rotation-invariant needlet convolution for rotation group SO(3) to distill multiscale information of spherical signals. The spherical needlet transform is gen…
Spectral Transform Forms Scalable Transformer
Bingxin Zhou, Xinliang Liu, Yuehua Liu +3
Many real-world relational systems, such as social networks and biological systems, contain dynamic interactions. When learning dynamic graph representation, it is essential to emp…
Can neural networks learn persistent homology features?
Guido Montúfar, Nina Otter, Yuguang Wang
Topological data analysis uses tools from topology -- the mathematical area that studies shapes -- to create representations of data. In particular, in persistent homology, one stu…
Deep Learning Based Unsupervised and Semi-supervised Classification for Keratoconus
Nicole Hallett, Kai Yi, Josef Dick +4
The transparent cornea is the window of the eye, facilitating the entry of light rays and controlling focusing the movement of the light within the eye. The cornea is critical, con…
CosmoVAE: Variational Autoencoder for CMB Image Inpainting
Kai Yi, Yi Guo, Yanan Fan +2
Cosmic microwave background radiation (CMB) is critical to the understanding of the early universe and precise estimation of cosmological constants. Due to the contamination of the…
PAN: Path Integral Based Convolution for Deep Graph Neural Networks
Zheng Ma, Ming Li, Yuguang Wang
Convolution operations designed for graph-structured data usually utilize the graph Laplacian, which can be seen as message passing between the adjacent neighbors through a generic…
Analysis of Framelet Transforms on a Simplex
Yu Guang Wang, Houying Zhu
In this paper, we construct framelets associated with a sequence of quadrature rules on the simplex in . We give the framelet transforms -- decomposition an…
A study on effectiveness of extreme learning machine
Yuguang Wang, Feilong Cao, Yubo Yuan
Extreme learning machine (ELM), proposed by Huang et al., has been shown a promising learning algorithm for single-hidden layer feedforward neural networks (SLFNs). Nevertheless, b…
Approximation by boolean sums of Jackson operators on the sphere
Yuguang Wang, Feilong Cao
This paper concerns the approximation by the Boolean sums of Jackson operators on the unit sphere of . We prove the following…
The Direct and Converse Inequalities for Jackson-Type Operators on Spherical Cap
Yuguang Wang, Feilong Cao
Approximation on the spherical cap is different from that on the sphere which requires us to construct new operators. This paper discusses the approximation on the spherical cap. T…
Approximation by Semigroups of Spherical Operators
Yuguang Wang, Feilong Cao
This paper discusses the approximation by %semigroups of operators of class () on the sphere and focuses on a class of so called exponential-type multiplier operator…