( events)   Timezone: »  
The 2020 schedule is still incomplete Program Highlights »
Tue Jul 14 07:00 AM -- 07:45 AM & Tue Jul 14 06:00 PM -- 06:45 PM (PDT)
Normalized Flat Minima: Exploring Scale Invariant Definition of Flat Minima for Neural Networks Using PAC-Bayesian Analysis
Yusuke Tsuzuku · Issei Sato · Masashi Sugiyama

The notion of flat minima has gained attention as a key metric of the generalization ability of deep learning models. However, current definitions of flatness are known to be sensitive to parameter rescaling. While some previous studies have proposed to rescale flatness metrics using parameter scales to avoid the scale dependence, the normalized metrics lose the direct theoretical connections between flat minima and generalization. In this paper, we first provide generalization error bounds using existing normalized flatness measures. Using the analysis, we then propose a novel normalized flatness metric. The proposed metric enjoys both direct theoretical connections and better empirical correlation to generalization error.