2 papers
cs.LO2024
Towards Automatic Linearization via SMT Solving
Jian Cao, Liyong Lin, Lele Li
Mathematical optimization is ubiquitous in modern applications. However, in practice, we often need to use nonlinear optimization models, for which the existing optimization tools…
cs.LG2023
Convex Dual Theory Analysis of Two-Layer Convolutional Neural Networks with Soft-Thresholding
Chunyan Xiong, Mengli Lu, Xiaotong Yu +4
Soft-thresholding has been widely used in neural networks. Its basic network structure is a two-layer convolution neural network with soft-thresholding. Due to the network's nature…