English
Related papers

Related papers: Stabilize Deep ResNet with A Sharp Scaling Factor …

200 papers

Deep learning models are often successfully trained using gradient descent, despite the worst case hardness of the underlying non-convex optimization problem. The key question is then under what conditions can one prove that optimization…

Machine Learning · Computer Science 2017-02-28 Alon Brutzkus , Amir Globerson

In this article we study the stochastic gradient descent (SGD) optimization method in the training of fully-connected feedforward artificial neural networks with ReLU activation. The main result of this work proves that the risk of the SGD…

Numerical Analysis · Mathematics 2022-09-28 Arnulf Jentzen , Adrian Riekert

With the growth of model and data sizes, a broad effort has been made to design pruning techniques that reduce the resource demand of deep learning pipelines, while retaining model performance. In order to reduce both inference and training…

Machine Learning · Computer Science 2026-02-24 Dayana Savostianova , Emanuele Zangrando , Gianluca Ceruti , Francesco Tudisco

Factorization-based gradient descent is a scalable and efficient algorithm for solving low-rank matrix completion. Recent progress in structured non-convex optimization has offered global convergence guarantees for gradient descent under…

Optimization and Control · Mathematics 2021-02-09 Trung Vu , Raviv Raich

We study nonparametric regression by an over-parameterized two-layer neural network trained by gradient descent (GD) in this paper. We show that, if the neural network is trained by GD with early stopping, then the trained network renders a…

Machine Learning · Statistics 2025-11-07 Yingzhen Yang , Ping Li

Residual networks (ResNets) have displayed impressive results in pattern recognition and, recently, have garnered considerable theoretical interest due to a perceived link with neural ordinary differential equations (neural ODEs). This link…

Machine Learning · Computer Science 2021-06-11 Alain-Sam Cohen , Rama Cont , Alain Rossier , Renyuan Xu

Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…

Computer Vision and Pattern Recognition · Computer Science 2021-12-10 Chengxi Ye , Xiong Zhou , Tristan McKinney , Yanfeng Liu , Qinggang Zhou , Fedor Zhdanov

Large machine learning models are revolutionary technologies of artificial intelligence whose bottlenecks include huge computational expenses, power, and time used both in the pre-training and fine-tuning process. In this work, we show that…

Quantum Physics · Physics 2024-01-15 Junyu Liu , Minzhao Liu , Jin-Peng Liu , Ziyu Ye , Yunfei Wang , Yuri Alexeev , Jens Eisert , Liang Jiang

We propose a globally convergent multilevel training method for deep residual networks (ResNets). The devised method can be seen as a novel variant of the recursive multilevel trust-region (RMTR) method, which operates in hybrid…

Machine Learning · Computer Science 2022-06-14 Alena Kopaničáková , Rolf Krause

We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.…

Machine Learning · Computer Science 2019-04-08 Dushyant Mehta , Kwang In Kim , Christian Theobalt

Recursive least-squares algorithms often use forgetting factors as a heuristic to adapt to non-stationary data streams. The first contribution of this paper rigorously characterizes the effect of forgetting factors for a class of online…

Machine Learning · Computer Science 2019-11-22 Jianjun Yuan , Andrew Lamperski

In this article we study fully-connected feedforward deep ReLU ANNs with an arbitrarily large number of hidden layers and we prove convergence of the risk of the GD optimization method with random initializations in the training of such…

Optimization and Control · Mathematics 2022-07-14 Arnulf Jentzen , Adrian Riekert

The symmetric low-rank matrix factorization serves as a building block in many learning tasks, including matrix recovery and training of neural networks. However, despite a flurry of recent research, the dynamics of its training via…

Machine Learning · Computer Science 2024-11-26 Hesameddin Mohammadi , Mohammad Tinati , Stephen Tu , Mahdi Soltanolkotabi , Mihailo R. Jovanović

Recently Grimmer [1] showed for smooth convex optimization by utilizing longer steps periodically, gradient descent's textbook $LD^2/2T$ convergence guarantees can be improved by constant factors, conjecturing an accelerated rate strictly…

Optimization and Control · Mathematics 2023-09-28 Benjamin Grimmer , Kevin Shu , Alex L. Wang

Implicit neural networks have become increasingly attractive in the machine learning community since they can achieve competitive performance but use much less computational resources. Recently, a line of theoretical works established the…

Machine Learning · Computer Science 2022-10-03 Tianxiang Gao , Hongyang Gao

Deep clustering can optimize representations of instances (i.e., representation learning) and explore the inherent data distribution (i.e., clustering) simultaneously, which demonstrates a superior performance over conventional clustering…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Qi Qian

We study the convergence of gradient flow for the training of deep neural networks. If Residual Neural Networks are a popular example of very deep architectures, their training constitutes a challenging optimization problem due notably to…

Machine Learning · Computer Science 2025-07-22 Raphaël Barboni , Gabriel Peyré , François-Xavier Vialard

Vanishing and exploding gradients are two of the main obstacles in training deep neural networks, especially in capturing long range dependencies in recurrent neural networks~(RNNs). In this paper, we present an efficient parametrization of…

Machine Learning · Computer Science 2018-03-28 Jiong Zhang , Qi Lei , Inderjit S. Dhillon

Network-based transfer learning allows the reuse of deep learning features with limited data, but the resulting models can be unnecessarily large. Although network pruning can improve inference efficiency, existing algorithms usually…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Ken C. L. Wong , Satyananda Kashyap , Mehdi Moradi

Commonly used optimization algorithms often show a trade-off between good generalization and fast training times. For instance, stochastic gradient descent (SGD) tends to have good generalization; however, adaptive gradient methods have…

Machine Learning · Computer Science 2023-06-14 Aditya Cowsik , Tankut Can , Paolo Glorioso