paper-with-me

Papers

Learning Compact Neural Networks with Regularization

2018-02-05 · ICML 2018 7 · Samet Oymak

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow neural networks. Our framework is general and covers weight-sharing (convolutional networks), sparsity (network pruning), and low-rank constraints among others. We first introduce covering dimension to quantify the complexity of the constraint set and provide insights on the generalization properties. Then, we show that proposed algorithms become well-behaved and local linear convergence occurs once the amount of data exceeds the covering dimension. Overall, our results demonstrate that near-optimal sample complexity is sufficient for efficient learning and illustrate how regularization can be beneficial to learn over-parameterized networks.

📄 PDF Abstract BibTeX arXiv:1802.01223

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Similar Papers 제목 키워드 기반

Filter Pruning using Hierarchical Group Sparse Regularization for Deep Convolutional Neural Networks

2020-11-04 · Kakeru Mitsuno, Takio Kurita

Since the convolutional neural networks are often trained with redundant parameters, it is possible to reduce redundant kernels or filters to obtain a compact network without dropping the classification accuracy. In this…

OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks

2019-05-28 · CVPR 2019 6 · Jiashi Li, Qi Qi, Jingyu Wang, Ce Ge 외

Channel pruning can significantly accelerate and compress deep neural networks. Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain …

Compacting Neural Network Classifiers via Dropout Training

2016-11-18 · Yotaro Kubo, George Tucker, Simon Wiesler

We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network …

speech-recognitionSpeech Recognition

Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness

2019-05-30 · Adnan Siraj Rakin, Zhezhi He, Li Yang, Yanzhi Wang 외

Deep Neural Network (DNN) trained by the gradient descent method is known to be vulnerable to maliciously perturbed adversarial input, aka. adversarial attack. As one of the countermeasures against adversarial attack, in…

Adversarial Attack

Convergence Rates for Regularized Optimal Transport via Quantization

2022-08-30 · Stephan Eckstein, Marcel Nutz

We study the convergence of divergence-regularized optimal transport as the regularization parameter vanishes. Sharp rates for general divergences including relative entropy or $L^{p}$ regularization, general transport c…

Quantization