English
Related papers

Related papers: Entropic Regularization in the Deep Linear Network

200 papers

In this paper, we study Discretized Neural Networks (DNNs) composed of low-precision weights and activations, which suffer from either infinite or zero gradients due to the non-differentiable discrete function during training. Most…

Machine Learning · Computer Science 2024-12-20 Jun Chen , Hanwen Chen , Mengmeng Wang , Guang Dai , Ivor W. Tsang , Yong Liu

We study the entanglement entropy of a random tensor network (RTN) using tools from free probability theory. Random tensor networks are simple toy models that help the understanding of the entanglement behavior of a boundary region in the…

Quantum Physics · Physics 2024-07-04 Khurshed Fitter , Faedi Loulidi , Ion Nechita

The theoretical explanation for deep neural network (DNN) is still an open problem. In this paper DNN is considered as a discrete-time dynamical system due to its layered structure. The complexity provided by the nonlinearity in the…

Machine Learning · Computer Science 2019-01-09 Husheng Li

Diagonal linear networks (DLNs) are a tractable model that captures several nontrivial behaviors in neural network training, such as initialization-dependent solutions and incremental learning. These phenomena are typically studied in…

Machine Learning · Statistics 2026-03-16 Sota Nishiyama , Masaaki Imaizumi

Dimensional regularization of Euclidean momentum space integrals is a highly successful technique in renormalization of quantum field theories. While it yields a straightforward algorithmic method, with which to evaluate diagrams beyond…

Mathematical Physics · Physics 2020-09-03 Juuso Österman

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate \emph{scaled} ResNet in the limit of infinitely deep and wide…

Machine Learning · Computer Science 2024-03-18 Yihang Chen , Fanghui Liu , Yiping Lu , Grigorios G. Chrysos , Volkan Cevher

We propose a general framework for neural network compression that is motivated by the Minimum Description Length (MDL) principle. For that we first derive an expression for the entropy of a neural network, which measures its complexity…

Machine Learning · Computer Science 2018-12-20 Simon Wiedemann , Arturo Marban , Klaus-Robert Müller , Wojciech Samek

Based on its great successes in inference and denosing tasks, Dictionary Learning (DL) and its related sparse optimization formulations have garnered a lot of research interest. While most solutions have focused on single layer…

Machine Learning · Computer Science 2021-04-22 Wen Tang , Emilie Chouzenoux , Jean-Christophe Pesquet , Hamid Krim

Works on implicit regularization have studied gradient trajectories during the optimization process to explain why deep networks favor certain kinds of solutions over others. In deep linear networks, it has been shown that gradient descent…

Machine Learning · Computer Science 2023-06-02 Dan Zhao

Deep neural networks have proved very successful on archetypal tasks for which large training sets are available, but when the training data are scarce, their performance suffers from overfitting. Many existing methods of reducing…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Wei Zhu , Qiang Qiu , Jiaji Huang , Robert Calderbank , Guillermo Sapiro , Ingrid Daubechies

Learning in Deep Neural Networks (DNN) takes place by minimizing a non-convex high-dimensional loss function, typically by a stochastic gradient descent (SGD) strategy. The learning process is observed to be able to find good minimizers…

Machine Learning · Computer Science 2020-03-12 Carlo Baldassi , Fabrizio Pittorino , Riccardo Zecchina

Neural networks are complex functions of both their inputs and parameters. Much prior work in deep learning theory analyzes the distribution of network outputs at a fixed a set of inputs (e.g. a training dataset) over random initializations…

Disordered Systems and Neural Networks · Physics 2025-04-08 Mike Winer , Boris Hanin

The key to generalization is controlling the complexity of the network. However, there is no obvious control of complexity -- such as an explicit regularization term -- in the training of deep networks for classification. We will show that…

Machine Learning · Computer Science 2020-04-14 Andrzej Banburski , Qianli Liao , Brando Miranda , Lorenzo Rosasco , Fernanda De La Torre , Jack Hidary , Tomaso Poggio

We consider in this work the problem of minimizing the von Neumann entropy under the constraints that the density of particles, the current, and the kinetic energy of the system is fixed at each point of space. The unique minimizer is a…

Mathematical Physics · Physics 2019-10-29 Romain Duboscq , Olivier Pinaud

As a non-linear extension of the classic Linear Discriminant Analysis(LDA), Deep Linear Discriminant Analysis(DLDA) replaces the original Categorical Cross Entropy(CCE) loss function with eigenvalue-based loss function to make a deep neural…

Computer Vision and Pattern Recognition · Computer Science 2022-06-14 Wen Lu

Although Deep Learning (DL) has achieved success in complex Artificial Intelligence (AI) tasks, it suffers from various notorious problems (e.g., feature redundancy, and vanishing or exploding gradients), since updating parameters in…

Machine Learning · Computer Science 2023-02-17 Yanhong Fei , Xian Wei , Yingjie Liu , Zhengyu Li , Mingsong Chen

We present a structure-preserving Eulerian algorithm for solving $L^2$-gradient flows and a structure-preserving Lagrangian algorithm for solving generalized diffusions. Both algorithms employ neural networks as tools for spatial…

Numerical Analysis · Mathematics 2024-04-16 Ziqing Hu , Chun Liu , Yiwei Wang , Zhiliang Xu

We apply concepts from manifold regularization to develop new regularization techniques for training locally stable deep neural networks. Our regularizers are based on a sparsification of the graph Laplacian which holds with high…

Machine Learning · Statistics 2020-09-24 Charles Jin , Martin Rinard

We consider networks, trained via stochastic gradient descent to minimize $\ell_2$ loss, with the training labels perturbed by independent noise at each iteration. We characterize the behavior of the training dynamics near any parameter…

Machine Learning · Computer Science 2020-07-23 Guy Blanc , Neha Gupta , Gregory Valiant , Paul Valiant

The entropic lattice Boltzmann framework proposed the construction of the discrete equilibrium by taking into consideration minimization of a discrete entropy functional. The effect of this form of the discrete equilibrium on properties of…

Fluid Dynamics · Physics 2023-03-16 S. A. Hosseini , I. V. Karlin