Michael K. Ng

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

Complex Diffusion Maps with $I ¨ $ -Parameterized Kernels Revealing Inherent Harmonic Representations

Tongzhen Dang, Weiyang Ding, Michael K. Ng

In this paper, we propose Complex Diffusion Maps (CDM), a novel diffusion mapping framework that aims to reveal the dominant complex harmonics of high-dimensional data. Inspired by…

cs.LG2026

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning

Yaru Liu, Michael K. Ng, Yiqi Gu

This paper investigates the deep learning optimization problem with softmax cross-entropy loss. We propose a layer separation strategy to alleviate the strong nonconvexity encounte…

Complex Diffusion Maps with I¨-Parameterized Kernels Revealing Inherent Harmonic Representations

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning

Complex Diffusion Maps with $I ¨ $ -Parameterized Kernels Revealing Inherent Harmonic Representations