Stronger generalization bounds for deep nets via a compression approach
ICML, pp. 254-263, 2018.
Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but do not as yet result in sample complexity bounds better than naive parameter counting. The current paper shows generalization bounds thatu0027re orders of magn...More
PPT (Upload PPT)