paper-with-me

홈 › Papers

Not All Samples Are Created Equal: Deep Learning with Importance Sampling

2018-03-02 · ICML 2018 7 · Angelos Katharopoulos, François Fleuret

Deep neural network training spends most of the computation on examples that are properly handled, and could be ignored. We propose to mitigate this phenomenon with a principled importance sampling scheme that focuses computation on "informative" examples, and reduces the variance of the stochastic gradients during training. Our contribution is twofold: first, we derive a tractable upper bound to the per-sample gradient norm, and second we derive an estimator of the variance reduction achieved with importance sampling, which enables us to switch it on when it will result in an actual speedup. The resulting scheme can be used by changing a few lines of code in a standard SGD procedure, and we demonstrate experimentally, on image classification, CNN fine-tuning, and RNN training, that for a fixed wall-clock time budget, it provides a reduction of the train losses of up to an order of magnitude and a relative improvement of test errors between 5% and 17%.

📄 PDF Abstract BibTeX arXiv:1803.00942

Code (2)

idiap/importance-sampling 공식 구현 tf
TruongThaoNguyen/kakurenbo pytorch

Tasks

Allimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Online Importance Sampling for Stochastic Gradient Optimization

2023-11-24 · Corentin Salaün, Xingchang Huang, Iliyan Georgiev, Niloy J. Mitra 외

Machine learning optimization often depends on stochastic gradient descent, where the precision of gradient estimation is vital for model performance. Gradients are calculated from mini-batches formed by uniformly select…

Computational Efficiency

BSGAN: A Novel Oversampling Technique for Imbalanced Pattern Recognitions

2023-05-16 · Md Manjurul Ahsan, Shivakumar Raman, Zahed Siddique

Class imbalanced problems (CIP) are one of the potential challenges in developing unbiased Machine Learning (ML) models for predictions. CIP occurs when data samples are not equally distributed between the two or multipl…

Generative Adversarial Network

Relative Importance Sampling for off-Policy Actor-Critic in Deep Reinforcement Learning

2018-10-30 · Mahammad Humayoo, Gengzhong Zheng, Xiaoqing Dong, Liming Miao 외

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($\pi$) and the behavior policy (b…

Deep Reinforcement LearningOpenAI Gymreinforcement-learningReinforcement Learning+1

Importance Sampling with Unequal Support

2016-11-10 · Philip S. Thomas, Emma Brunskill

Importance sampling is often used in machine learning when training and testing data come from different distributions. In this paper we propose a new variant of importance sampling that can reduce the variance of import…

Supervised Contrastive Learning with Hard Negative Samples

2022-08-31 · Ruijie Jiang, Thuan Nguyen, Prakash Ishwar, Shuchin Aeron

Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close to each other while pushing negative samp…

Contrastive LearningSelf-Supervised Learning