8 citations · 32 across the 42 of their papers we have counts for
8 papers · 1 filter
Rieoptax: Riemannian Optimization in JAX
Saiteja Utpala, Andi Han, Pratik Jawanpuria +1
We present Rieoptax, an open source Python library for Riemannian optimization in JAX. We show that many differential geometric primitives, such as Riemannian exponential and logar…
Generalized energy and gradient flow via graph framelets
Andi Han, Dai Shi, Zhiqi Shao +1
In this work, we provide a theoretical understanding of the framelet-based graph neural networks through the perspective of energy gradient flow. By viewing the framelet-based mode…
Generalized Laplacian Regularized Framelet Graph Neural Networks
Zhiqi Shao, Andi Han, Dai Shi +2
This paper introduces a novel Framelet Graph approach based on p-Laplacian GNN. The proposed two models, named p-Laplacian undecimated framelet graph convolution (pL-UFG) and gener…
Riemannian accelerated gradient methods via extrapolation
Andi Han, Bamdev Mishra, Pratik Jawanpuria +1
In this paper, we propose a simple acceleration scheme for Riemannian gradient methods by extrapolating iterates on manifolds. We show when the iterates are generated from Riemanni…
Differentially private Riemannian optimization
Andi Han, Bamdev Mishra, Pratik Jawanpuria +1
In this paper, we study the differentially private empirical risk minimization problem where the parameter is constrained to a Riemannian manifold. We introduce a framework of diff…
A Simple Yet Effective SVD-GCN for Directed Graphs
Chunya Zou, Andi Han, Lequan Lin +1
In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN. The new…