paper-with-me

Papers

On Rademacher Complexity-based Generalization Bounds for Deep Learning

2022-08-08 · Lan V. Truong

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.

📄 PDF Abstract BibTeX arXiv:2208.04284

Code (0)

등록된 구현이 없습니다.

Tasks

Deep LearningGeneralization Bounds

Similar Papers 제목 키워드 기반

Rademacher Complexity Bounds for Non-I.I.D. Processes

2008-12-01 · NeurIPS 2008 12 · Mehryar Mohri, Afshin Rostamizadeh

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 Bounds

Human Rademacher Complexity

2009-12-01 · NeurIPS 2009 12 · Jerry Zhu, Bryan R. Gibson, Timothy T. Rogers

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 Theory

Hypothesis Set Stability and Generalization

2019-04-09 · NeurIPS 2019 12 · Dylan J. Foster, Spencer Greenberg, Satyen Kale, Haipeng Luo 외

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

2015-10-06 · Yunwen Lei, Lixin Ding, Yingzhou Bi

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

2023-07-04 · Sarah Sachs, Tim van Erven, Liam Hodgkinson, Rajiv Khanna 외

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