paper-with-me

홈 › Papers

Cogradient Descent for Bilinear Optimization

2020-06-16 · CVPR 2020 6 · Li'an Zhuo, Baochang Zhang, Linlin Yang, Hanlin Chen, Qixiang Ye, David Doermann, Guodong Guo, Rongrong Ji

Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure. One reason lies in the insufficient training due to the asynchronous gradient descent, which results in vanishing gradients for the coupled variables. In this paper, we introduce a Cogradient Descent algorithm (CoGD) to address the bilinear problem, based on a theoretical framework to coordinate the gradient of hidden variables via a projection function. We solve one variable by considering its coupling relationship with the other, leading to a synchronous gradient descent to facilitate the optimization procedure. Our algorithm is applied to solve problems with one variable under the sparsity constraint, which is widely used in the learning paradigm. We validate our CoGD considering an extensive set of applications including image reconstruction, inpainting, and network pruning. Experiments show that it improves the state-of-the-art by a significant margin.

📄 PDF Abstract BibTeX arXiv:2006.09142

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionNetwork Pruning

Similar Papers 제목 키워드 기반

Cogradient Descent for Dependable Learning

2021-06-20 · Runqi Wang, Baochang Zhang, Li'an Zhuo, Qixiang Ye 외

Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative. Treating the coupled variables independently while ignoring the interaction, however, leads to an insuffi…

Image InpaintingImage ReconstructionNetwork Pruning

Nesterov Meets Optimism: Rate-Optimal Separable Minimax Optimization

2022-10-31 · Chris Junchi Li, Angela Yuan, Gauthier Gidel, Quanquan Gu 외

We propose a new first-order optimization algorithm -- AcceleratedGradient-OptimisticGradient (AG-OG) Descent Ascent -- for separable convex-concave minimax optimization. The main idea of our algorithm is to carefully le…

Last-iterate convergence rates for min-max optimization

2019-06-05 · ICLR 2020 1 · Jacob Abernethy, Kevin A. Lai, Andre Wibisono

While classic work in convex-concave min-max optimization relies on average-iterate convergence results, the emergence of nonconvex applications such as training Generative Adversarial Networks has led to renewed interes…

Sparse Bilinear Logistic Regression

2014-04-15 · Jianing V. Shi, Yangyang Xu, Richard G. Baraniuk

In this paper, we introduce the concept of sparse bilinear logistic regression for decision problems involving explanatory variables that are two-dimensional matrices. Such problems are common in computer vision, brain-c…

regression

Dissipative Gradient Descent Ascent Method: A Control Theory Inspired Algorithm for Min-max Optimization

2024-03-14 · Tianqi Zheng, Nicolas Loizou, Pengcheng You, Enrique Mallada

Gradient Descent Ascent (GDA) methods for min-max optimization problems typically produce oscillatory behavior that can lead to instability, e.g., in bilinear settings. To address this problem, we introduce a dissipation…