On Rademacher Complexity-based Generalization Bounds for Deep Learning
We show that the Rademacher complexity-based approach can generate non-vacuous generalisation bounds on Convolutional Neural Networks (CNNs) for classifying a small number of classes of images. The development of new Talagrand's contraction lemmas for high-dimensional mappings between function spaces and CNNs for general Lipschitz activation functions is a key technical contribution. Our results show that the Rademacher complexity does not depend on the network length for CNNs with some special types of activation functions such as ReLU, Leaky ReLU, Parametric Rectifier Linear Unit, Sigmoid, and Tanh.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningGeneralization BoundsSimilar Papers 제목 키워드 기반
Rademacher Complexity Bounds for Non-I.I.D. Processes
This paper presents the first data-dependent generalization bounds for non-i.i.d. settings based on the notion of Rademacher complexity. Our bounds extend to the non-i.i.d. case existing Rademacher complexity bounds deri…
Generalization BoundsHuman Rademacher Complexity
We propose to use Rademacher complexity, originally developed in computational learning theory, as a measure of human learning capacity. Rademacher complexity measures a learners ability to fit random data, and can be u…
Generalization BoundsLearning TheoryHypothesis Set Stability and Generalization
We present a study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main result is…
Local Rademacher Complexity Bounds based on Covering Numbers
This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate the complexities with constraint on the expected norm to the corresponding ones with constrai…
Generalization Guarantees via Algorithm-dependent Rademacher Complexity
Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms. In this context, there exists information theoretic generalization bounds tha…
Generalization Bounds