Exploring the convergence of the loss landscape in neural networks as the sample size increases, focusing on the Hessian matrix to understand the local geometry of the loss function
The method proposed is the first linearly convergent first-order decentralized algorithm for problems with general affine coupled constraints
Presenting two approaches to determining a sufficient sample size based on the proximity of posterior distributions of model parameters on similar subsets
Exploring the correlation between video sequences and fMRI images, using a linear autoregressive model