paper-with-me

Papers

Stochastic Gradient Descent with Hyperbolic-Tangent Decay on Classification

2018-06-05 · Bo Yang Hsueh, Wei Li, I-Chen Wu

Learning rate scheduler has been a critical issue in the deep neural network training. Several schedulers and methods have been proposed, including step decay scheduler, adaptive method, cosine scheduler and cyclical scheduler. This paper proposes a new scheduling method, named hyperbolic-tangent decay (HTD). We run experiments on several benchmarks such as: ResNet, Wide ResNet and DenseNet for CIFAR-10 and CIFAR-100 datasets, LSTM for PAMAP2 dataset, ResNet on ImageNet and Fashion-MNIST datasets. In our experiments, HTD outperforms step decay and cosine scheduler in nearly all cases, while requiring less hyperparameters than step decay, and more flexible than cosine scheduler. Code is available at https://github.com/BIGBALLON/HTD.

📄 PDF Abstract BibTeX arXiv:1806.01593

Code (5)

BIGBALLON/HTD 공식 구현 pytorch
MindSpore-scientific-2/code-5/tree/main/cyclic-cosine-decay-master mindspore
MindSpore-scientific/code-4/tree/main/cyclic-cosine-decay-master mindspore
karthikRavichandran/LR_exploration_tf tf
pwc-1/Paper-9/tree/main/4/cyclic-cosine-decay-master mindspore

Tasks

ClassificationGeneral ClassificationScheduling

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Average Pooling 설명 없음
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…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…

Similar Papers 제목 키워드 기반

Convergence of stochastic gradient descent schemes for Lojasiewicz-landscapes

2021-02-16 · Steffen Dereich, Sebastian Kassing

In this article, we consider convergence of stochastic gradient descent schemes (SGD), including momentum stochastic gradient descent (MSGD), under weak assumptions on the underlying landscape. More explicitly, we show t…

A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks

2020-02-10 · NeurIPS 2020 12 · Zixiang Chen, Yuan Cao, Quanquan Gu, Tong Zhang

A recent breakthrough in deep learning theory shows that the training of over-parameterized deep neural networks can be characterized by a kernel function called \textit{neural tangent kernel} (NTK). However, it is known…

Learning TheoryVocal Bursts Valence Prediction

Optimal Rates for Averaged Stochastic Gradient Descent under Neural Tangent Kernel Regime

2020-06-22 · ICLR 2021 1 · Atsushi Nitanda, Taiji Suzuki

We analyze the convergence of the averaged stochastic gradient descent for overparameterized two-layer neural networks for regression problems. It was recently found that a neural tangent kernel (NTK) plays an important …

Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximations

2022-06-07 · Nurendra Choudhary, Chandan K. Reddy

Hyperbolic networks have shown prominent improvements over their Euclidean counterparts in several areas involving hierarchical datasets in various domains such as computer vision, graph analysis, and natural language pr…

Anatomy

Neural ODEs as the Deep Limit of ResNets with constant weights

2019-06-28 · arXiv 2019 6 · Benny Avelin, Kaj Nyström

In this paper we prove that, in the deep limit, the stochastic gradient descent on a ResNet type deep neural network, where each layer shares the same weight matrix, converges to the stochastic gradient descent for a Neu…