[D] Are there any results on convergence guarantees when optimizing NNs? Submitted by Dartagnjan t3_10ee9kp on January 17, 2023 at 2:57 PM in MachineLearning 10 comments 11
[D] Techniques to optimize a model when the loss over the training dataset has a Power Law type curve. Submitted by Dartagnjan t3_zqtmf7 on December 20, 2022 at 5:04 PM in MachineLearning 22 comments 107