paper-with-me

Papers

On the Regularization Properties of Structured Dropout

2019-10-30 · CVPR 2020 6 · Ambar Pal, Connor Lane, René Vidal, Benjamin D. Haeffele

Dropout and its extensions (eg. DropBlock and DropConnect) are popular heuristics for training neural networks, which have been shown to improve generalization performance in practice. However, a theoretical understanding of their optimization and regularization properties remains elusive. Recent work shows that in the case of single hidden-layer linear networks, Dropout is a stochastic gradient descent method for minimizing a regularized loss, and that the regularizer induces solutions that are low-rank and balanced. In this work we show that for single hidden-layer linear networks, DropBlock induces spectral k-support norm regularization, and promotes solutions that are low-rank and have factors with equal norm. We also show that the global minimizer for DropBlock can be computed in closed form, and that DropConnect is equivalent to Dropout. We then show that some of these results can be extended to a general class of Dropout-strategies, and, with some assumptions, to deep non-linear networks when Dropout is applied to the last layer. We verify our theoretical claims and assumptions experimentally with commonly used network architectures.

📄 PDF Abstract BibTeX arXiv:1910.14186

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

DropBlock DropBlock is a structured form of dropout directed at regularizing convolutional networks. In DropBlock, units in a contiguous…
DropConnect DropConnect generalizes Dropout by randomly dropping the weights rather than the activations with probability $1-p$. DropConnect…
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…

Similar Papers 제목 키워드 기반

Structured Dropout Variational Inference for Bayesian Neural Networks

2021-02-16 · NeurIPS 2021 12 · Son Nguyen, Duong Nguyen, Khai Nguyen, Khoat Than 외

Approximate inference in Bayesian deep networks exhibits a dilemma of how to yield high fidelity posterior approximations while maintaining computational efficiency and scalability. We tackle this challenge by introducin…

Bayesian InferenceComputational EfficiencyOut-of-Distribution DetectionVariational Inference

Dropout as a Structured Shrinkage Prior

2018-10-09 · Eric Nalisnick, José Miguel Hernández-Lobato, Padhraic Smyth

Dropout regularization of deep neural networks has been a mysterious yet effective tool to prevent overfitting. Explanations for its success range from the prevention of "co-adapted" weights to it being a form of cheap B…

Bayesian Inference

Information Geometry of Dropout Training

2022-06-22 · Masanari Kimura, Hideitsu Hino

Dropout is one of the most popular regularization techniques in neural network training. Because of its power and simplicity of idea, dropout has been analyzed extensively and many variants have been proposed. In this pa…

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…

Revisiting Structured Dropout

2022-10-05 · Yiren Zhao, Oluwatomisin Dada, Xitong Gao, Robert D Mullins

Large neural networks are often overparameterised and prone to overfitting, Dropout is a widely used regularization technique to combat overfitting and improve model generalization. However, unstructured Dropout is not a…

Scheduling