5 papers
Backpropagation-Free Trunk Training via the Split Forward Gradients
Tian Qin, Wei-Min Huang
Backpropagation makes training deep networks memory intensive because it must store intermediate activations. Forward-mode methods avoid this cost, but their gradient estimates bec…
Ricci-Filtration: Boosting Retrieval-Augmented Generation Reranker to Query-Answer Tasks by Discrete Ricci Flow
Tian Qin, Wei-Min Huang
Ricci flow is a curvature-guided diffusion process that deforms space by shrinking regions of high positive curvature and expanding those with negative curvature. Similarly, discre…
On Kernel-based Variational Autoencoder
Tian Qin, Wei-Min Huang
In this paper, we bridge Variational Autoencoders (VAEs) and kernel density estimations (KDEs) by approximating the posterior by KDEs and deriving an upper bound of the Kullback-Le…
Debiasing Kernel-Based Generative Models
Tian Qin, Wei-Min Huang
We propose a novel two-stage framework of generative models named Debiasing Kernel-Based Generative Models (DKGM) with the insights from kernel density estimation (KDE) and stochas…
Riemann-Lebesgue Forest for Regression
Tian Qin, Wei-Min Huang
We propose a novel ensemble method called Riemann-Lebesgue Forest (RLF) for regression. The core idea in RLF is to mimic the way how a measurable function can be approximated by pa…