paper-with-me

Papers

Dropout Drops Double Descent

2023-05-25 · Tian-Le Yang, Joe Suzuki

This study demonstrates that double descent can be mitigated by adding a dropout layer adjacent to the fully connected linear layer. The unexpected double-descent phenomenon garnered substantial attention in recent years, resulting in fluctuating prediction error rates as either sample size or model size increases. Our paper posits that the optimal test error, in terms of the dropout rate, shows a monotonic decrease in linear regression with increasing sample size. Although we do not provide a precise mathematical proof of this statement, we empirically validate through experiments that the test error decreases for each dropout rate. The statement we prove is that the expected test error for each dropout rate within a certain range decreases when the dropout rate is fixed. Our experimental results substantiate our claim, showing that dropout with an optimal dropout rate can yield a monotonic test error curve in nonlinear neural networks. These experiments were conducted using the Fashion-MNIST and CIFAR-10 datasets. These findings imply the potential benefit of incorporating dropout into risk curve scaling to address the peak phenomenon. To our knowledge, this study represents the first investigation into the relationship between dropout and double descent.

📄 PDF Abstract BibTeX arXiv:2305.16179

Code (0)

등록된 구현이 없습니다.

Tasks

regression

Methods 이 논문이 사용한 방법론

Test 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Linear Regression Linear Regression is a method for modelling a relationship between a dependent variable and independent variables. These models can be fit with numerous approaches. The most…

Similar Papers 제목 키워드 기반

When and how epochwise double descent happens

2021-08-26 · Cory Stephenson, Tyler Lee

Deep neural networks are known to exhibit a `double descent' behavior as the number of parameters increases. Recently, it has also been shown that an `epochwise double descent' effect exists in which the generalization e…

Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle

2023-03-24 · Rylan Schaeffer, Mikail Khona, Zachary Robertson, Akhilan Boopathy 외

Double descent is a surprising phenomenon in machine learning, in which as the number of model parameters grows relative to the number of data, test error drops as models grow ever larger into the highly overparameterize…

Learning Theoryregression

DropCluster: A structured dropout for convolutional networks

2020-02-07 · Liyan Chen, Philip Gautier, Sergul Aydore

Dropout as a regularizer in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is due to the fact that dropout drops features randomly. When features are spatially c…

Dropout Regularization in Extended Generalized Linear Models based on Double Exponential Families

2023-05-11 · Benedikt Lütke Schwienhorst, Lucas Kock, Nadja Klein, David J. Nott

Even though dropout is a popular regularization technique, its theoretical properties are not fully understood. In this paper we study dropout regularization in extended generalized linear models based on double exponent…

MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning

2021-08-03 · Wanpeng Zhang, Xi Xiao, Yao Yao, Mingzhe Chen 외

Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catas…

Model-based Reinforcement Learning