paper-with-me

홈 › Papers

Tight Sample Complexity of Learning One-hidden-layer Convolutional Neural Networks

2019-11-12 · NeurIPS 2019 12 · Yuan Cao, Quanquan Gu

We study the sample complexity of learning one-hidden-layer convolutional neural networks (CNNs) with non-overlapping filters. We propose a novel algorithm called approximate gradient descent for training CNNs, and show that, with high probability, the proposed algorithm with random initialization grants a linear convergence to the ground-truth parameters up to statistical precision. Compared with existing work, our result applies to general non-trivial, monotonic and Lipschitz continuous activation functions including ReLU, Leaky ReLU, Sigmod and Softplus etc. Moreover, our sample complexity beats existing results in the dependency of the number of hidden nodes and filter size. In fact, our result matches the information-theoretic lower bound for learning one-hidden-layer CNNs with linear activation functions, suggesting that our sample complexity is tight. Our theoretical analysis is backed up by numerical experiments.

📄 PDF Abstract BibTeX arXiv:1911.05059

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
(TravEL!!Guide)How Do I File a Claim with Expedia? How Do I File a Claim with Expedia? Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Fast Help & Exclusive Travel Discounts!Need to file a claim with…

Similar Papers 제목 키워드 기반

Generalization bounds for graph convolutional neural networks via Rademacher complexity

2021-02-20 · Shaogao Lv

This paper aims at studying the sample complexity of graph convolutional networks (GCNs), by providing tight upper bounds of Rademacher complexity for GCN models with a single hidden layer. Under regularity conditions, t…

Generalization Bounds

The Sample Complexity of One-Hidden-Layer Neural Networks

2022-02-13 · Gal Vardi, Ohad Shamir, Nathan Srebro

We study norm-based uniform convergence bounds for neural networks, aiming at a tight understanding of how these are affected by the architecture and type of norm constraint, for the simple class of scalar-valued one-hid…

How Many Samples are Needed to Estimate a Convolutional Neural Network?

2018-12-01 · NeurIPS 2018 12 · Simon S. Du, Yining Wang, Xiyu Zhai, Sivaraman Balakrishnan 외

A widespread folklore for explaining the success of Convolutional Neural Networks (CNNs) is that CNNs use a more compact representation than the Fully-connected Neural Network (FNN) and thus require fewer training sample…

LEMMA

Guaranteed Recovery of One-Hidden-Layer Neural Networks via Cross Entropy

2018-02-18 · ICLR 2019 5 · Haoyu Fu, Yuejie Chi, Yingbin Liang

We study model recovery for data classification, where the training labels are generated from a one-hidden-layer neural network with sigmoid activations, also known as a single-layer feedforward network, and the goal is …

On the Sample Complexity of One Hidden Layer Networks with Equivariance, Locality and Weight Sharing

2024-11-21 · Arash Behboodi, Gabriele Cesa

Weight sharing, equivariance, and local filters, as in convolutional neural networks, are believed to contribute to the sample efficiency of neural networks. However, it is not clear how each one of these design choices …

Learning Theory