6 papers · 1 filter
MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-Regularized Optimization
Luxuan Li, Chunfeng Cui, Xiao Wang
In this paper, we study a structured class of nonconvex constrained stochastic problems with difference-of-convex (DC) regularization, where the feasible set is possibly nonconvex…
Blind Hyperspectral and Multispectral Images Fusion: A Unified Tensor Fusion Framework from Coupled Inverse Problem Perspective
Ying Gao, Michael K. Ng, Chunfeng cui
Hyperspectral and multispectral images fusion aims at integrating a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HR-MSI) to construct a hi…
Narrowing the Gap: SOS Ranks of Biquadratic Forms and a Lower Bound of
Yi Xu, Chunfeng Cui, Liqun Qi
We investigate the maximum sum-of-squares (SOS) rank of biquadratic forms in the critical case of variables, where the general bounds are currently $7 \leq \mathrm{BSR…
Parallelizable Riemannian Alternating Direction Method of Multipliers for Non-convex Pose Graph Optimization
Xin Chen, Chunfeng Cui, Deren Han +1
Pose graph optimization (PGO) is fundamental to robot perception and navigation systems, serving as the mathematical backbone for solving simultaneous localization and mapping (SLA…
DualHash: A Stochastic Primal-Dual Algorithm with Theoretical Guarantee for Deep Hashing
Luxuan Li, Xiao Wang, Chunfeng Cui
Deep hashing converts high-dimensional feature vectors into compact binary codes, enabling efficient large-scale retrieval. A fundamental challenge in deep hashing stems from the d…
Multi-step Inertial Accelerated Doubly Stochastic Gradient Methods for Block Term Tensor Decomposition
Zehui Liu, Qingsong Wang, Chunfeng Cui
In this paper, we explore a specific optimization problem that combines a differentiable nonconvex function with a nondifferentiable function for multi-block variables, which is pa…