https://openreview.net/forum?id=RusKt9aoTON&referrer=%5Bthe%20profile%20of%20Yi%20Zhao%5D(%2Fprofile%3Fid%3D~Yi_Zhao10)
This paper interprets federated learning algorithms with Gradient Signal to Noise Ratio and proposes the corresponding method to accelerate model convergence...
federated learningacceleratingnoniiddata
https://blog.demofox.org/2022/01/01/interleaved-gradient-noise-a-different-kind-of-low-discrepancy-sequence/
The python code that goes along with this post can be found at In 2014, Jorge Jimenez from Activision presented a type of noise optimized for use with Temporal...
low discrepancy sequencegradient noiseinterleaveddifferentkind