English
Related papers

Related papers: Algorithmic Regularization in Learning Deep Homoge…

200 papers

We study the problem of training deep neural networks with Rectified Linear Unit (ReLU) activation function using gradient descent and stochastic gradient descent. In particular, we study the binary classification problem and show that for…

Machine Learning · Computer Science 2018-12-31 Difan Zou , Yuan Cao , Dongruo Zhou , Quanquan Gu

We study the problem of learning one-hidden-layer neural networks with Rectified Linear Unit (ReLU) activation function, where the inputs are sampled from standard Gaussian distribution and the outputs are generated from a noisy teacher…

Machine Learning · Statistics 2018-06-21 Xiao Zhang , Yaodong Yu , Lingxiao Wang , Quanquan Gu

We consider stochastic gradient methods under the interpolation regime where a perfect fit can be obtained (minimum loss at each observation). While previous work highlighted the implicit regularization of such algorithms, we consider an…

Optimization and Control · Mathematics 2020-04-01 Anant Raj , Francis Bach

We prove that two-layer (Leaky)ReLU networks initialized by e.g. the widely used method proposed by He et al. (2015) and trained using gradient descent on a least-squares loss are not universally consistent. Specifically, we describe a…

Machine Learning · Statistics 2022-06-10 David Holzmüller , Ingo Steinwart

A surprising phenomenon in the training of neural networks is the ability of gradient descent to find global minimizers of the training loss despite its non-convexity. Following earlier works, we investigate this behavior for wide shallow…

Optimization and Control · Mathematics 2026-05-12 Romain Petit , Clarice Poon , Gabriel Peyré

Among many mysteries behind the success of deep networks lies the exceptional discriminative power of their learned representations as manifested by the intriguing Neural Collapse (NC) phenomenon, where simple feature structures emerge at…

Machine Learning · Computer Science 2025-10-27 Hancheng Min , Zhihui Zhu , René Vidal

We give a simple local Polyak-Lojasiewicz (PL) criterion that guarantees linear (exponential) convergence of gradient flow and gradient descent to a zero-loss solution of a nonnegative objective. We then verify this criterion for the…

Machine Learning · Computer Science 2026-02-23 Sourav Chatterjee

The momentum acceleration technique is widely adopted in many optimization algorithms. However, there is no theoretical answer on how the momentum affects the generalization performance of the optimization algorithms. This paper studies…

Machine Learning · Computer Science 2022-05-30 Bohan Wang , Qi Meng , Huishuai Zhang , Ruoyu Sun , Wei Chen , Zhi-Ming Ma , Tie-Yan Liu

Gradient descent is one of the most widely used iterative algorithms in modern statistical learning. However, its precise algorithmic dynamics in high-dimensional settings remain only partially understood, which has limited its broader…

Statistics Theory · Mathematics 2025-11-19 Qiyang Han , Xiaocong Xu

Classical optimisation theory guarantees monotonic objective decrease for gradient descent (GD) when employed in a small step size, or ``stable", regime. In contrast, gradient descent on neural networks is frequently performed in a large…

Machine Learning · Computer Science 2025-10-21 Lachlan Ewen MacDonald , Hancheng Min , Leandro Palma , Salma Tarmoun , Ziqing Xu , René Vidal

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

Natural gradient descent is a principled method for adapting the parameters of a statistical model on-line using an underlying Riemannian parameter space to redefine the direction of steepest descent. The algorithm is examined via methods…

Disordered Systems and Neural Networks · Physics 2009-10-31 Magnus Rattray , David Saad

We investigate implicit regularization schemes for gradient descent methods applied to unpenalized least squares regression to solve the problem of reconstructing a sparse signal from an underdetermined system of linear measurements under…

Machine Learning · Statistics 2019-09-12 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

One of the most important parts of Artificial Neural Networks is minimizing the loss functions which tells us how good or bad our model is. To minimize these losses we need to tune the weights and biases. Also to calculate the minimum value…

Machine Learning · Computer Science 2021-01-08 Kaustubh Yadav

Understanding the dynamics of optimization in deep learning is increasingly important as models scale. While stochastic gradient descent (SGD) and its variants reliably find solutions that generalize well, the mechanisms driving this…

Machine Learning · Computer Science 2026-04-07 Wei-Kai Chang , Rajiv Khanna

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

We derive explicit equations governing the cumulative biases and weights in Deep Learning with ReLU activation function, based on gradient descent for the Euclidean cost in the input layer, and under the assumption that the weights are, in…

Machine Learning · Computer Science 2025-01-15 Thomas Chen

A main puzzle of deep networks revolves around the absence of overfitting despite large overparametrization and despite the large capacity demonstrated by zero training error on randomly labeled data. In this note, we show that the dynamics…

Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously analyzes the convergence properties of gradient flow in…

Machine Learning · Statistics 2024-11-01 Cheng Gao , Yuan Cao , Zihao Li , Yihan He , Mengdi Wang , Han Liu , Jason Matthew Klusowski , Jianqing Fan

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich