Deep Learning
78ed45281dd746a265fff16ff75a02e5-Paper-Conference.pdf
Unfortunately, these theoretical results cannot well explain the empirical successes of deep learning well, as they require the model size tobenolargerthan O(n)(thegeneralization boundsbecomevacuousotherwise).
Neural Collapse To Multiple Centers For Imbalanced Data
NC phenomena occur with different loss functions.
Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models
However, it has several unique challenges.
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
This has motivated numerous studies aiming to reduce the variance and improve convergence of FL on non-IID data [6, 9, 14, 17, 19, 30]. On another note, constraints on communication resources and therefore on the number of clients that may participate in training additionally complicate implementation of FL schemes.