English
Related papers

Related papers: Dropout Regularization Versus $\ell_2$-Penalizatio…

200 papers

The inference performance of the pseudolikelihood method is discussed in the framework of the inverse Ising problem when the $\ell_2$-regularized (ridge) linear regression is adopted. This setup is introduced for theoretically investigating…

Disordered Systems and Neural Networks · Physics 2021-10-19 Xiangming Meng , Tomoyuki Obuchi , Yoshiyuki Kabashima

When an online learning algorithm is used to estimate the unknown parameters of a model, the signals interacting with the parameter estimates should not decay too quickly for the optimal values to be discovered correctly. This requirement…

Machine Learning · Computer Science 2019-11-05 Kamil Nar , S. Shankar Sastry

The Ridgeless minimum $\ell_2$-norm interpolator in overparametrized linear regression has attracted considerable attention in recent years in both machine learning and statistics communities. While it seems to defy conventional wisdom that…

Statistics Theory · Mathematics 2026-01-21 Qiyang Han , Xiaocong Xu

We investigate the phenomenon of grokking -- delayed generalization accompanied by non-monotonic test loss behavior -- in a simple binary logistic classification task, for which "memorizing" and "generalizing" solutions can be strictly…

Machine Learning · Statistics 2025-07-22 Alon Beck , Noam Levi , Yohai Bar-Sinai

We derive a divergence formula for a group of regularization methods with an L2 constraint. The formula is useful for regularization parameter selection, because it provides an unbiased estimate for the number of degrees of freedom. We…

Other Statistics · Statistics 2012-03-19 Yixin Fang , Yuanjia Wang , Xin Huang

Dropout regularization has been widely used in deep learning but performs less effective for convolutional neural networks since the spatially correlated features allow dropped information to still flow through the networks. Some structured…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Hui Zhu , Xiaofang Zhao

The study on the implicit regularization induced by gradient-based optimization is a longstanding pursuit. In the present paper, we characterize the implicit regularization of momentum gradient descent (MGD) with early stopping by comparing…

Machine Learning · Computer Science 2022-01-17 Li Wang , Yingcong Zhou , Zhiguo Fu

Existing theory suggests that for linear regression problems categorized by capacity and source conditions, gradient descent (GD) is always minimax optimal, while both ridge regression and online stochastic gradient descent (SGD) are…

Machine Learning · Statistics 2025-09-23 Jingfeng Wu , Peter L. Bartlett , Jason D. Lee , Sham M. Kakade , Bin Yu

This paper shows that the implicit bias of gradient descent on linearly separable data is exactly characterized by the optimal solution of a dual optimization problem given by a smoothed margin, even for general losses. This is in contrast…

Machine Learning · Computer Science 2020-11-13 Ziwei Ji , Matus Telgarsky

Dropout has been witnessed with great success in training deep neural networks by independently zeroing out the outputs of neurons at random. It has also received a surge of interest for shallow learning, e.g., logistic regression. However,…

Machine Learning · Computer Science 2016-12-06 Zhe Li , Boqing Gong , Tianbao Yang

The effects of several nonlinear regularization techniques are discussed in the framework of 3D seismic tomography. Traditional, linear, $\ell_2$ penalties are compared to so-called sparsity promoting $\ell_1$ and $\ell_0$ penalties, and a…

Geophysics · Physics 2010-08-19 I. Loris , H. Douma , G. Nolet , I. Daubechies , C. Regone

This work considers the effect of averaging, and more generally extrapolation, of the iterates of gradient descent in smooth convex optimization. After running the method, rather than reporting the final iterate, one can report either a…

Optimization and Control · Mathematics 2025-05-29 Alan Luner , Benjamin Grimmer

Dropout is typically interpreted as bagging a large number of models sharing parameters. We show that using dropout in a network can also be interpreted as a kind of data augmentation in the input space without domain knowledge. We present…

Machine Learning · Statistics 2016-01-11 Xavier Bouthillier , Kishore Konda , Pascal Vincent , Roland Memisevic

A key challenge in building theoretical foundations for deep learning is the complex optimization dynamics of neural networks, resulting from the high-dimensional interactions between the large number of network parameters. Such non-trivial…

Machine Learning · Computer Science 2021-12-07 Mohammad Pezeshki , Amartya Mitra , Yoshua Bengio , Guillaume Lajoie

In the context of linear inverse problems, we propose and study a general iterative regularization method allowing to consider large classes of regularizers and data-fit terms. The algorithm we propose is based on a primal-dual diagonal…

Optimization and Control · Mathematics 2017-08-04 Guillaume Garrigos , Lorenzo Rosasco , Silvia Villa

Epoch-wise double descent is the phenomenon where generalisation performance improves beyond the point of overfitting, resulting in a generalisation curve exhibiting two descents under the course of learning. Understanding the mechanisms…

Machine Learning · Statistics 2024-09-20 Amanda Olmin , Fredrik Lindsten

Deep Neural Networks often require good regularizers to generalize well. Dropout is one such regularizer that is widely used among Deep Learning practitioners. Recent work has shown that Dropout can also be viewed as performing Approximate…

Machine Learning · Computer Science 2016-11-22 Suraj Srinivas , R. Venkatesh Babu

Unsupervised pretraining and dropout have been well studied, especially with respect to regularization and output consistency. However, our understanding about the explicit convergence rates of the parameter estimates, and their dependence…

Machine Learning · Computer Science 2017-02-23 Vamsi K. Ithapu , Sathya Ravi , Vikas Singh

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Xu Shen , Xinmei Tian , Tongliang Liu , Fang Xu , Dacheng Tao