A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Re-initializing neural networks improves generalization but not as much as other techniques.
Understanding deep neural networks is a major research objective with notable experimental and theoretical attention in recent years. The practical success of excessively large networks underscores the need for better theoretical analyses and justifications. In this paper we focus on layer-wise functional structure and…
RIFLE improves deep transfer learning by reinitializing fully-connected layers.
Over the past years Robust PCA has been established as a standard tool for reliable low-rank approximation of matrices in the presence of outliers. Recently, the Robust PCA approach via nuclear norm minimization has been extended to matrices with linear structures which appear in applications such as system identificat…
AGS-CL selectively updates penalties based on node importance for continual learning.
A scalable method for deep metric learning using chance constraints.
Study on rich regime training in deep learning, finding active parameters in bottom layers.
A new method for neural network initialization using graph degeneracy.
Improved training for VQ-VAE models with robust codebook learning.