Robuta

https://arxiv.org/html/2410.13849v1 From Gradient Clipping to Normalization for Heavy Tailed SGD gradient clippingheavy tailednormalizationsgd https://github.com/dmizr/phuber GitHub - dmizr/phuber: [Re] Can gradient clipping mitigate label noise? (ML Reproducibility... [Re] Can gradient clipping mitigate label noise? (ML Reproducibility Challenge 2020) - dmizr/phuber re cangradient clipping