[Tip] Reduce the batch size to generalize your model

[MicPie (Michael)]

Hey @dhoa,

I guess this posted paper in another thread goes in a similar direction and could be interesting:

New Google paper proposing to increase Batch Size instead of decaying Learning Rate

With a shouting tilte DON’T DECAY THE LEARNING RATE, INCREASE THE BATCH SIZE https://arxiv.org/pdf/1711.00489.pdf

I’m curious and will try this out soon.

Best regards
Michael