Tsinghua U Proposes Stochastic Scheduled Sharpness-Aware Minimization for Efficient DNN Training | Synced
A Tsinghua University research team proposes Stochastic Scheduled SAM (SS-SAM), a novel and efficient DNN training scheme that achieves comparable or better model training performance with much low...
Source: Synced | AI Technology & Industry Review
A Tsinghua University research team proposes Stochastic Scheduled SAM (SS-SAM), a novel and efficient DNN training scheme that achieves comparable or better model training performance with much lower computation cost compared to baseline sharpness-aware minimization (SAM) training schema.