@inproceedings{0a25d195baa54c47b315f46dc7cdff03,

title = "Learning deep ResNet blocks sequentially using boosting theory",

abstract = "We prove a multi-channel telescoping sum boosting theory for the ResNet architectures which simultaneously creates a new technique for boosting over features (in contrast to labels) and provides a new algorithm for ResNet-style architectures. Our proposed training algorithm, BoostRes-Net, is particularly suitable in non-differentiable architectures. Our method only requires the relatively inexpensive sequential training of T {"}shallow ResNets{"}. We prove that the training error decays exponentially with the depth T if the weak module classifiers that we train perform slightly better than some weak baseline. In other words, we propose a weak learning condition and prove a boosting theory for ResNet under the weak learning condition. A generalization error bound based on margin theory is proved and suggests that ResNet could be resistant to overfitting using a network with l1 norm bounded weights.",

author = "Furong Huang and Ash, {Jordan T.} and John Langford and Schapire, {Robert E.}",

year = "2018",

month = jan,

day = "1",

language = "English (US)",

series = "35th International Conference on Machine Learning, ICML 2018",

publisher = "International Machine Learning Society (IMLS)",

pages = "3272--3290",

editor = "Jennifer Dy and Andreas Krause",

booktitle = "35th International Conference on Machine Learning, ICML 2018",

note = "35th International Conference on Machine Learning, ICML 2018 ; Conference date: 10-07-2018 Through 15-07-2018",

}