English
Related papers

Related papers: How You Start Matters for Generalization

200 papers

Our understanding of the generalization capabilities of neural networks (NNs) is still incomplete. Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from…

Machine Learning · Computer Science 2025-05-01 Damien Teney , Armand Nicolicioiu , Valentin Hartmann , Ehsan Abbasnejad

It has been observed in practice that applying pruning-at-initialization methods to neural networks and training the sparsified networks can not only retain the testing performance of the original dense models, but also sometimes even…

Machine Learning · Computer Science 2023-01-31 Hongru Yang , Yingbin Liang , Xiaojie Guo , Lingfei Wu , Zhangyang Wang

We analyze single-layer neural networks with the Xavier initialization in the asymptotic regime of large numbers of hidden units and large numbers of stochastic gradient descent training steps. The evolution of the neural network during…

Probability · Mathematics 2022-04-13 Justin Sirignano , Konstantinos Spiliopoulos

Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and…

Machine Learning · Computer Science 2018-11-08 Hao Li , Zheng Xu , Gavin Taylor , Christoph Studer , Tom Goldstein

A widely believed explanation for the remarkable generalization capacities of overparameterized neural networks is that the optimization algorithms used for training induce an implicit bias towards benign solutions. To grasp this…

Machine Learning · Computer Science 2025-12-19 Maria Matveev , Vit Fojtik , Hung-Hsu Chou , Gitta Kutyniok , Johannes Maly

Generalization to unseen degradations remains a fundamental challenge for low-level vision models. This paper aims to investigate the underlying mechanism of this failure, using image deraining as a primary case study due to its…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Jinfan Hu , Zhiyuan You , Jinjin Gu , Kaiwen Zhu , Tianfan Xue , Chao Dong

This work provides an additional step in the theoretical understanding of neural networks. We consider neural networks with one hidden layer and show that when learning symmetric functions, one can choose initial conditions so that standard…

Machine Learning · Computer Science 2019-07-02 Ido Nachum , Amir Yehudayoff

In this paper we propose a Bayesian method for estimating architectural parameters of neural networks, namely layer size and network depth. We do this by learning concrete distributions over these parameters. Our results show that regular…

Machine Learning · Statistics 2019-01-29 Georgi Dikov , Patrick van der Smagt , Justin Bayer

While previous optimization results have suggested that deep neural networks tend to favour low-rank weight matrices, the implications of this inductive bias on generalization bounds remain underexplored. In this paper, we apply Maurer's…

Machine Learning · Computer Science 2024-11-22 Andrea Pinto , Akshay Rangamani , Tomaso Poggio

Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for…

Machine Learning · Computer Science 2019-03-13 Hongyi Zhang , Yann N. Dauphin , Tengyu Ma

Deep neural networks are typically initialized with random weights, with variances chosen to facilitate signal propagation and stable gradients. It is also believed that diversity of features is an important property of these…

Machine Learning · Computer Science 2020-07-03 Yaniv Blumenfeld , Dar Gilboa , Daniel Soudry

Neural networks have attracted a lot of attention due to its success in applications such as natural language processing and computer vision. For large scale data, due to the tremendous number of parameters in neural networks, overfitting…

Machine Learning · Statistics 2022-07-05 Xiaoxi Shen , Jinghang Lin

Batch Normalization (BN) improves both convergence and generalization in training neural networks. This work understands these phenomena theoretically. We analyze BN by using a basic block of neural networks, consisting of a kernel layer, a…

Machine Learning · Computer Science 2019-04-25 Ping Luo , Xinjiang Wang , Wenqi Shao , Zhanglin Peng

Deep neural networks are renowned for their ability to generalise well across diverse tasks, even when heavily overparameterized. Existing works offer only partial explanations (for example, the NTK-based task-model alignment explanation…

Machine Learning · Computer Science 2025-06-02 Chris Mingard , Lukas Seier , Niclas Göring , Andrei-Vlad Badelita , Charles London , Ard Louis

Factorized layers--operations parameterized by products of two or more matrices--occur in a variety of deep learning contexts, including compressed model training, certain types of knowledge distillation, and multi-head self-attention…

Machine Learning · Statistics 2022-10-07 Mikhail Khodak , Neil Tenenholtz , Lester Mackey , Nicolò Fusi

In the realm of computer vision, Neural Fields have gained prominence as a contemporary tool harnessing neural networks for signal representation. Despite the remarkable progress in adapting these networks to solve a variety of problems,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Hemanth Saratchandran , Sameera Ramasinghe , Simon Lucey

We develop regularization methods to find flat minima while training deep neural networks. These minima generalize better than sharp minima, yielding models outperforming baselines on real-world test data (which may be distributed…

Machine Learning · Computer Science 2025-07-04 Adam Sandler , Diego Klabjan , Yuan Luo

Normalization layers were introduced to stabilize and accelerate training, yet their influence is critical already at initialization, where they shape signal propagation and output statistics before parameters adapt to data. In practice,…

Machine Learning · Computer Science 2026-04-03 Emanuele Francazi , Francesco Pinto , Aurelien Lucchi , Marco Baity-Jesi

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

Overparameterized neural networks often show a benign overfitting property in the sense of achieving excellent generalization behavior despite the number of parameters exceeding the number of training examples. A promising direction to…

Machine Learning · Computer Science 2026-04-23 Yunwen Lei , Yufeng Xie