Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 1 of 1 for “"Adaptive Gradient Method"”.
-
EFFECTIVE TRAINING OF NEURAL NETWORKS FOR BETTER GENERALIZATION
… stability. We propose DRAG, a dimension-reduced adaptive gradient method that unifies the benefits of SGD and Adam, and a memory-efficient Shampoo using 4-bit Cholesky quantization with error feedback, enabling scalable second-order training. From the data side, we investigate why data-centric …