3 problems

0 votes0 replies0 views
Conjecture on extending benign overfitting theory to super-wide deep neural networks
StoNet conjecture. The StoNet could enable the extension of benign overfitting theory from linear models to super-wide DNNs by leveraging its capability in sufficient dimension red…
Conjectureopenbenign-overfitting deep-learning-theory sufficient-dimension-reductionarXiv posted 2 days ago
0 votes0 replies0 views
Conjectured tight convergence rate for the output error in large-scale ResNets
Output-space rate conjecture. The tight rate for $\Delta_k^y$ should be
Conjectureopenconvergence-rates deep-learning-theory random-matrix-theoryarXiv posted 2 days ago
0 votes0 replies0 views
Progressive Feedforward Collapse conjecture for ResNet training
Progressive Feedforward Collapse conjecture. At the terminal phase of ResNet training, neural collapse emerges in the last-layer features. Before the effective depth, there exists…
Conjectureopendeep-learning-theory neural-collapse resnetarXiv posted 2 days ago

Conjecture on extending benign overfitting theory to super-wide deep neural networks