English
Related papers

Related papers: Modify Training Directions in Function Space to Re…

200 papers

In previous studies, we introduced a neural network framework based on symmetric differential equations, along with one of its training methods. In this article, we present another training approach for this neural network. This method…

Neural and Evolutionary Computing · Computer Science 2025-02-18 Kun Jiang

In order to better understand feature learning in neural networks, we propose a framework for understanding linear models in tangent feature space where the features are allowed to be transformed during training. We consider linear…

Machine Learning · Computer Science 2024-02-22 Daniel LeJeune , Sina Alemohammad

Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs), yet their Gauss--Newton update must be solved in the parameter space, incurring a prohibitive $O(n^3)$ time complexity, where $n$ is the…

Machine Learning · Computer Science 2025-10-09 Anas Jnini , Flavio Vella

Distributed learning provides an attractive framework for scaling the learning task by sharing the computational load over multiple nodes in a network. Here, we investigate the performance of distributed learning for large-scale linear…

Machine Learning · Statistics 2021-11-03 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization…

Numerical Analysis · Mathematics 2026-02-26 Chenguang Liu , Antonis Papapantoleon , Jasper Rou

In this paper we introduce a novel method of gradient normalization and decay with respect to depth. Our method leverages the simple concept of normalizing all gradients in a deep neural network, and then decaying said gradients with…

Machine Learning · Computer Science 2018-03-01 Robert Kwiatkowski , Oscar Chang

Sequential training from task to task is becoming one of the major objects in deep learning applications such as continual learning and transfer learning. Nevertheless, it remains unclear under what conditions the trained model's…

Machine Learning · Statistics 2022-03-21 Ryo Karakida , Shotaro Akaho

Representing signals using coordinate networks dominates the area of inverse problems recently, and is widely applied in various scientific computing tasks. Still, there exists an issue of spectral bias in coordinate networks, limiting the…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Zhicheng Cai , Hao Zhu , Qiu Shen , Xinran Wang , Xun Cao

We study the learning performance of gradient descent when the empirical risk is weakly convex, namely, the smallest negative eigenvalue of the empirical risk's Hessian is bounded in magnitude. By showing that this eigenvalue can control…

Machine Learning · Statistics 2021-06-02 Dominic Richards , Mike Rabbat

Normalization layers are widely used in deep neural networks to stabilize training. In this paper, we consider the training of convolutional neural networks with gradient descent on a single training example. This optimization problem…

Machine Learning · Computer Science 2019-07-24 Zhenwei Dai , Reinhard Heckel

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

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

The performance of the data-dependent neural tangent kernel (NTK; Jacot et al. (2018)) associated with a trained deep neural network (DNN) often matches or exceeds that of the full network. This implies that DNN training via gradient…

Machine Learning · Computer Science 2025-05-22 Johannes Schwab , Bryan Kelly , Semyon Malamud , Teng Andrea Xu

Recent work across many machine learning disciplines has highlighted that standard descent methods, even without explicit regularization, do not merely minimize the training error, but also exhibit an implicit bias. This bias is typically…

Machine Learning · Computer Science 2020-06-22 Ziwei Ji , Miroslav Dudík , Robert E. Schapire , Matus Telgarsky

Generative Adversarial Networks (GANs) are a popular formulation to train generative models for complex high dimensional data. The standard method for training GANs involves a gradient descent-ascent (GDA) procedure on a minimax…

Machine Learning · Computer Science 2023-05-30 Evan Becker , Parthe Pandit , Sundeep Rangan , Alyson K. Fletcher

Parameter-space regularization in neural network optimization is a fundamental tool for improving generalization. However, standard parameter-space regularization methods make it challenging to encode explicit preferences about desired…

Machine Learning · Statistics 2023-12-29 Tim G. J. Rudner , Sanyam Kapoor , Shikai Qiu , Andrew Gordon Wilson

The flexibility of decision boundaries in neural networks that are unguided by training data is a well-known problem typically resolved with generalization methods. A surprising result from recent knowledge distillation (KD) literature is…

Machine Learning · Computer Science 2024-10-28 HeeSeung Jung , Kangil Kim , Hoyong Kim , Jong-Hun Shin

Recent results on optimization and generalization properties of neural networks showed that in a simple two-layer network, the alignment of the labels to the eigenvectors of the corresponding Gram matrix determines the convergence of the…

Machine Learning · Computer Science 2023-02-03 Arman Rahbar , Emilio Jorge , Devdatt Dubhashi , Morteza Haghir Chehreghani

Natural gradient descent has a remarkable property that in the small learning rate limit, it displays an invariance with respect to network reparameterizations, leading to robust training behavior even for highly covariant network…

Machine Learning · Statistics 2023-12-11 Christian Goodbrake

In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian…

Machine Learning · Computer Science 2026-04-02 Deyi Kong , Zaiwei Chen , Shuzhong Zhang , Shancong Mou