Tweeted By @fhuszar
Arguing that large-batch doesn't generalize well: https://t.co/DCFmkK5yWu
— Ferenc Huszár🇪🇺 (@fhuszar) August 15, 2019
Arguing that full batch GD does in fact generalize:https://t.co/nUXQJEu2LV (Table 1)
Arguing that large-batch doesn't generalize well: https://t.co/DCFmkK5yWu
— Ferenc Huszár🇪🇺 (@fhuszar) August 15, 2019
Arguing that full batch GD does in fact generalize:https://t.co/nUXQJEu2LV (Table 1)