English
Related papers

Related papers: On Dropout and Nuclear Norm Regularization

200 papers

Deep neural networks (DNNs) have become increasingly important due to their excellent empirical performance on a wide range of problems. However, regularization is generally achieved by indirect means, largely due to the complex set of…

Machine Learning · Computer Science 2018-07-02 Amal Rannen Triki , Maxim Berman , Matthew B. Blaschko

The layered structure of deep neural networks hinders the use of numerous analysis tools and thus the development of its interpretability. Inspired by the success of functional brain networks, we propose a novel framework for…

Machine Learning · Computer Science 2022-05-25 Ben Zhang , Zhetong Dong , Junsong Zhang , Hongwei Lin

The present paper deals with the data-driven design of regularizers in the form of artificial neural networks, for solving certain inverse problems formulated as optimal control problems. These regularizers aim at improving accuracy,…

Optimization and Control · Mathematics 2023-03-06 Sebastien Court

Subspace identification is a classical and very well studied problem in system identification. The problem was recently posed as a convex optimization problem via the nuclear norm relaxation. Inspired by robust PCA, we extend this framework…

Systems and Control · Computer Science 2013-12-10 Dorsa Sadigh , Henrik Ohlsson , S. Shankar Sastry , Sanjit A. Seshia

We discuss several aspects of the loss landscape of regularized neural networks: the structure of stationary points, connectivity of optimal solutions, path with nonincreasing loss to arbitrary global optimum, and the nonuniqueness of…

Machine Learning · Computer Science 2025-04-30 Sungyoon Kim , Aaron Mishkin , Mert Pilanci

We pursue a line of research that seeks to regularize the spectral norm of the Jacobian of the input-output mapping for deep neural networks. While previous work rely on upper bounding techniques, we provide a scheme that targets the exact…

Machine Learning · Statistics 2022-06-29 Anton Johansson , Claes Strannegård , Niklas Engsner , Petter Mostad

While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking. We introduce the concept of \emph{weight expansion}, an increase in the signed volume of a…

Machine Learning · Computer Science 2022-09-13 Gaojie Jin , Xinping Yi , Pengfei Yang , Lijun Zhang , Sven Schewe , Xiaowei Huang

We show that the training problem of a deep linear neural network under the squared loss admits an exact convex reformulation in a lifted space over a generalized completely positive cone. The reformulation has the same optimal value as the…

Machine Learning · Computer Science 2026-05-19 Karthik Prakhya , Alp Yurtsever

Deep neural networks are over-parameterized, which implies that the number of parameters are much larger than the number of samples used to train the network. Even in such a regime deep architectures do not overfit. This phenomenon is an…

Machine Learning · Computer Science 2019-02-01 Mayank Sharma , Aayush Yadav , Sumit Soman , Jayadeva

Inspired by the adaptation phenomenon of neuronal firing, we propose the regularity normalization (RN) as an unsupervised attention mechanism (UAM) which computes the statistical regularity in the implicit space of neural networks under the…

Machine Learning · Computer Science 2021-12-30 Baihan Lin

This paper is concerned with the problem of representing and learning a linear transformation using a linear neural network. In recent years, there has been a growing interest in the study of such networks in part due to the successes of…

Optimization and Control · Mathematics 2017-09-28 Amirhossein Taghvaei , Jin W. Kim , Prashant G. Mehta

In this paper, we made an extension to the convergence analysis of the dynamics of two-layered bias-free networks with one $ReLU$ output. We took into consideration two popular regularization terms: the $\ell_1$ and $\ell_2$ norm of the…

Machine Learning · Statistics 2017-11-21 Zhifeng Kong

We analyze the convergence rate of gradient flows on objective functions induced by Dropout and Dropconnect, when applying them to shallow linear Neural Networks (NNs) - which can also be viewed as doing matrix factorization using a…

Machine Learning · Computer Science 2020-12-04 Albert Senen-Cerda , Jaron Sanders

We study training of Convolutional Neural Networks (CNNs) with ReLU activations and introduce exact convex optimization formulations with a polynomial complexity with respect to the number of data samples, the number of neurons, and data…

Machine Learning · Computer Science 2021-03-19 Tolga Ergen , Mert Pilanci

Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks. However, due to the model capacity required to capture such representations, they are often…

Computer Vision and Pattern Recognition · Computer Science 2017-11-30 Terrance DeVries , Graham W. Taylor

Deep Neural Networks have achieved remarkable success relying on the developing high computation capability of GPUs and large-scale datasets with increasing network depth and width in image recognition, object detection and many other…

Machine Learning · Computer Science 2020-01-08 E Zhenqian , Gao Weiguo

This paper proposes a new regularization algorithm referred to as macro-block dropout. The overfitting issue has been a difficult problem in training large neural network models. The dropout technique has proven to be simple yet very…

Machine Learning · Computer Science 2023-01-02 Chanwoo Kim , Sathish Indurti , Jinhwan Park , Wonyong Sung

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 exponential families, for…

Machine Learning · Statistics 2024-07-30 Benedikt Lütke Schwienhorst , Lucas Kock , Nadja Klein , David J. Nott

This paper investigates theoretical properties and efficient numerical algorithms for the so-called elastic-net regularization originating from statistics, which enforces simultaneously l^1 and l^2 regularization. The stability of the…

Numerical Analysis · Mathematics 2015-05-13 Bangti Jin , Dirk Lorenz , Stefan Schiffler

Modern machine learning models are often trained in a setting where the number of parameters exceeds the number of training samples. To understand the implicit bias of gradient descent in such overparameterized models, prior work has…

Machine Learning · Statistics 2025-10-29 Hannes Matt , Dominik Stöger
‹ Prev 1 3 4 5 6 7 10 Next ›