3 papers
cs.LG2026
Grokking or Glitching? How Low-Precision Drives Slingshot Loss Spikes
Liu Hanqing, Jianjun Cao, Yuanze Li +1
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…
stat.ML2026
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…
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…