paper-with-me

홈 › Papers

Towards Understanding Label Smoothing

2020-06-20 · Yi Xu, Yuanhong Xu, Qi Qian, Hao Li, Rong Jin

Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants. However, the theoretical understanding of its power from the view of optimization is still rare. This study opens the door to a deep understanding of LSR by initiating the analysis. In this paper, we analyze the convergence behaviors of stochastic gradient descent with label smoothing regularization for solving non-convex problems and show that an appropriate LSR can help to speed up the convergence by reducing the variance. More interestingly, we proposed a simple yet effective strategy, namely Two-Stage LAbel smoothing algorithm (TSLA), that uses LSR in the early training epochs and drops it off in the later training epochs. We observe from the improved convergence result of TSLA that it benefits from LSR in the first stage and essentially converges faster in the second stage. To the best of our knowledge, this is the first work for understanding the power of LSR via establishing convergence complexity of stochastic methods with LSR in non-convex optimization. We empirically demonstrate the effectiveness of the proposed method in comparison with baselines on training ResNet models over benchmark data sets.

📄 PDF Abstract BibTeX arXiv:2006.11653

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
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…
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Batch Normalization 설명 없음
Average Pooling 설명 없음
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
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

An Investigation of how Label Smoothing Affects Generalization

2020-10-23 · Blair Chen, Liu Ziyin, ZiHao Wang, Paul Pu Liang

It has been hypothesized that label smoothing can reduce overfitting and improve generalization, and current empirical evidence seems to corroborate these effects. However, there is a lack of mathematical understanding o…

Understanding Generalized Label Smoothing when Learning with Noisy Labels

2021-09-29 · Jiaheng Wei, Hangyu Liu, Tongliang Liu, Gang Niu 외

Label smoothing (LS) is an arising learning paradigm that uses the positively weighted average of both the hard training labels and uniformly distributed soft labels. It was shown that LS serves as a regularizer for trai…

Learning with noisy labels

Cross Entropy versus Label Smoothing: A Neural Collapse Perspective

2024-02-06 · Li Guo, Keith Ross, Zifan Zhao, George Andriopoulos 외

Label smoothing loss is a widely adopted technique to mitigate overfitting in deep neural networks. This paper studies label smoothing from the perspective of Neural Collapse (NC), a powerful empirical and theoretical fr…

Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing

2020-05-02 · ACL 2020 6 · Clara Meister, Elizabeth Salesky, Ryan Cotterell

Prior work has explored directly regularizing the output distributions of probabilistic models to alleviate peaky (i.e. over-confident) predictions, a common sign of overfitting. This class of techniques, of which label …

Text Generation

Towards a Better Understanding of Label Smoothing in Neural Machine Translation

2020-12-01 · Asian Chapter of the Association for Computational Linguistics 2020 · Yingbo Gao, Weiyue Wang, Christian Herold, Zijian Yang 외

In order to combat overfitting and in pursuit of better generalization, label smoothing is widely applied in modern neural machine translation systems. The core idea is to penalize over-confident outputs and regularize t…

Machine TranslationTranslation