4 papers
Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
Hanqing Liu, Liu Hanqing, Jianjun Cao +2
Deep neural networks exhibit periodic loss spikes during unregularized long-term training, a phenomenon known as the "Slingshot Mechanism." Existing work usually attributes this to…
Permutation-preserving Functions and Neural Vecchia Covariance Kernels
Jian Cao, Nian Liu, Ying Lin
We introduce a novel framework for constructing scalable and flexible covariance kernels for Gaussian processes (GPs) by directly learning the covariance structure under a regressi…
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…
Alternating Deep Low-Rank Approach for Exponential Function Reconstruction and Its Biomedical Magnetic Resonance Applications
Yihui Huang, Zi Wang, Xinlin Zhang +5
Undersampling can accelerate the signal acquisition but at the cost of bringing in artifacts. Removing these artifacts is a fundamental problem in signal processing and this task i…