mixup: Beyond Empirical Risk Minimization mixup: Beyond Empirical Risk Minimization
Paper summary Very efficient data augmentation method. Linear-interpolate training set x and y randomly at every epoch. ```python for (x1, y1), (x2, y2) in zip(loader1, loader2): lam = numpy.random.beta(alpha, alpha) x = Variable(lam * x1 + (1. - lam) * x2) y = Variable(lam * y1 + (1. - lam) * y2) optimizer.zero_grad() loss(net(x), y).backward() optimizer.step() ``` - ERM (Empirical Risk Minimization) is $\alpha = 0$ version of mixup, i.e. not using mixup. - Reduces the memorization of corrupt labels. - Increases robustness to adversarial examples. - Stabilizes the training of GAN.
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang and Moustapha Cisse and Yann N. Dauphin and David Lopez-Paz
arXiv e-Print archive - 2017 via Local arXiv
Keywords: cs.LG, stat.ML


Summary by daisukelab 3 years ago
Your comment:

ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!

Sponsored by: and