English
Related papers

Related papers: Dropout Drops Double Descent

200 papers

As one of standard approaches to train deep neural networks, dropout has been applied to regularize large models to avoid overfitting, and the improvement in performance by dropout has been explained as avoiding co-adaptation between nodes.…

Machine Learning · Computer Science 2019-10-10 Sangchul Hahn , Heeyoul Choi

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to these demands, but we…

Machine Learning · Computer Science 2019-04-23 Sungrae Park , Kyungwoo Song , Mingi Ji , Wonsung Lee , Il-Chul Moon

It is important to understand how the popular regularization method dropout helps the neural network training find a good generalization solution. In this work, we show that the training with dropout finds the neural network with a flatter…

Machine Learning · Computer Science 2022-05-24 Zhongwang Zhang , Hanxu Zhou , Zhi-Qin John Xu

We observe a novel 'multiple-descent' phenomenon during the training process of LSTM, in which the test loss goes through long cycles of up and down trend multiple times after the model is overtrained. By carrying out asymptotic stability…

Machine Learning · Computer Science 2025-05-27 Wenbo Wei , Nicholas Chong Jia Le , Choy Heng Lai , Ling Feng

Algorithmic approaches endow deep learning systems with implicit bias that helps them generalize even in over-parametrized settings. In this paper, we focus on understanding such a bias induced in learning through dropout, a popular…

Machine Learning · Computer Science 2018-06-27 Poorya Mianjy , Raman Arora , Rene Vidal

Overfitting is a common problem in machine learning, which means the model too closely fits the training data while performing poorly in the test data. Among various methods of coping with overfitting, dropout is one of the representative…

Machine Learning · Computer Science 2022-05-17 Yangkun Li , Weizhi Ma , Chong Chen , Min Zhang , Yiqun Liu , Shaoping Ma , Yuekui Yang

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

Overparametrized models can exhibit an excellent generalization performance, although they should be prone to overfitting according to classical statistical theory. The discovery of the "double descent", indicating that the generalization…

Machine Learning · Computer Science 2026-05-22 Tino Werner

A recent line of research has highlighted the existence of a "double descent" phenomenon in deep learning, whereby increasing the number of training examples $N$ causes the generalization error of neural networks to peak when $N$ is of the…

Machine Learning · Computer Science 2022-01-12 Stéphane d'Ascoli , Levent Sagun , Giulio Biroli

Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a…

Machine Learning · Computer Science 2021-06-04 Xiao Zhang , Dongrui Wu , Haoyi Xiong , Bo Dai

Dropout is a simple but effective technique for learning in neural networks and other settings. A sound theoretical understanding of dropout is needed to determine when dropout should be applied and how to use it most effectively. In this…

Machine Learning · Computer Science 2017-02-21 David P. Helmbold , Philip M. Long

The appearance of the double-descent risk phenomenon has received growing interest in the machine learning and statistics community, as it challenges well-understood notions behind the U-shaped train-test curves. Motivated through…

Machine Learning · Statistics 2020-11-11 Prasad Cheema , Mahito Sugiyama

Increasing the size of overparameterized neural networks has been a key in achieving state-of-the-art performance. This is captured by the double descent phenomenon, where the test loss follows a decreasing-increasing-decreasing pattern (or…

Machine Learning · Computer Science 2024-05-09 Yihao Xue , Kyle Whitecross , Baharan Mirzasoleiman

Predictive multiplicity refers to the phenomenon in which classification tasks may admit multiple competing models that achieve almost-equally-optimal performance, yet generate conflicting outputs for individual samples. This presents…

Machine Learning · Computer Science 2024-02-02 Hsiang Hsu , Guihong Li , Shaohan Hu , Chun-Fu , Chen

Uncertainty quantification in a neural network is one of the most discussed topics for safety-critical applications. Though Neural Networks (NNs) have achieved state-of-the-art performance for many applications, they still provide…

Machine Learning · Computer Science 2022-05-09 Mehedi Hasan , Abbas Khosravi , Ibrahim Hossain , Ashikur Rahman , Saeid Nahavandi

Modern deep learning models employ considerably more parameters than required to fit the training data. Whereas conventional statistical wisdom suggests such models should drastically overfit, in practice these models generalize remarkably…

Machine Learning · Statistics 2020-08-18 Ben Adlam , Jeffrey Pennington

Classical learning theory suggests that the optimal generalization performance of a machine learning model should occur at an intermediate model complexity, with simpler models exhibiting high bias and more complex models exhibiting high…

Machine Learning · Statistics 2020-11-09 Ben Adlam , Jeffrey Pennington

We show how to adjust for the variance introduced by dropout with corrections to weight initialization and Batch Normalization, yielding higher accuracy. Though dropout can preserve the expected input to a neuron between train and test, the…

Machine Learning · Computer Science 2017-03-27 Dan Hendrycks , Kevin Gimpel

Dropout training, originally designed for deep neural networks, has been successful on high-dimensional single-layer natural language tasks. This paper proposes a theoretical explanation for this phenomenon: we show that, under a generative…

Machine Learning · Statistics 2014-11-03 Stefan Wager , William Fithian , Sida Wang , Percy Liang

Despite the importance of denoising in modern machine learning and ample empirical work on supervised denoising, its theoretical understanding is still relatively scarce. One concern about studying supervised denoising is that one might not…

Machine Learning · Computer Science 2024-03-18 Chinmaya Kausik , Kashvi Srivastava , Rishi Sonthalia