English
Related papers

Related papers: A Spectral Condition for Feature Learning

200 papers

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

Invariances to translations have imbued convolutional neural networks with powerful generalization properties. However, we often do not know a priori what invariances are present in the data, or to what extent a model should be invariant to…

Machine Learning · Computer Science 2020-12-02 Gregory Benton , Marc Finzi , Pavel Izmailov , Andrew Gordon Wilson

In this paper, we propose a machine learning model, which dynamically changes the features during training. Our main motivation is to update the model in a small content during the training process with replacing less descriptive features…

Machine Learning · Computer Science 2020-02-24 Marcell Beregi-Kovács , Ágnes Baran , András Hajdu

Foundation models have achieved remarkable success, yet their growing parameter counts pose significant computational and memory challenges. Low-rank factorization offers a promising route to reduce training and inference costs, but the…

Machine Learning · Computer Science 2026-02-16 Paul Janson , Edouard Oyallon , Eugene Belilovsky

This paper proposes a novel approach to improve the training efficiency and the generalization performance of Feed Forward Neural Networks (FFNNs) resorting to an optimal rescaling of input features (OFR) carried out by a Genetic Algorithm…

Machine Learning · Computer Science 2024-02-21 Federico Maria Vitrò , Marco Leonesio , Lorenzo Fagiano

Spectral bias is an important observation of neural network training, stating that the network will learn a low frequency representation of the target function before converging to higher frequency components. This property is interesting…

Machine Learning · Computer Science 2023-05-05 John Lazzari , Xiuwen Liu

We address three key challenges in learning continuous kernel representations: computational efficiency, parameter efficiency, and spectral bias. Continuous kernels have shown significant potential, but their practical adoption is often…

Machine Learning · Computer Science 2024-09-17 Clayton Harper , Luke Wood , Peter Gerstoft , Eric C. Larson

Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…

Computer Vision and Pattern Recognition · Computer Science 2020-03-12 Byungju Kim , Junmo Kim

Understanding the internal representations learned by neural networks is a cornerstone challenge in the science of machine learning. While there have been significant recent strides in some cases towards understanding how neural networks…

Machine Learning · Computer Science 2024-02-20 Depen Morwani , Benjamin L. Edelman , Costin-Andrei Oncescu , Rosie Zhao , Sham Kakade

Several variations of adaptive first-order and second-order optimization methods have been proposed to accelerate and scale the training of large language models. The performance of these optimization routines is highly sensitive to the…

Machine Learning · Computer Science 2026-02-25 Akshita Gupta , Marieme Ngom , Sam Foreman , Venkatram Vishwanath

Majority of the current dimensionality reduction or retrieval techniques rely on embedding the learned feature representations onto a computable metric space. Once the learned features are mapped, a distance metric aids the bridging of gaps…

Computer Vision and Pattern Recognition · Computer Science 2018-10-17 Muhammad Kamran Janjua , Shah Nawaz , Alessandro Calefati , Ignazio Gallo

The mechanism governing the training dynamics of Quantum Neural Networks (QNNs) remains under-explored. In classical Deep Neural Networks (DNNs), training is dominated by "Spectral Bias," i.e. prioritizing learning low-frequency components…

Quantum Physics · Physics 2025-12-25 Yi-hang Xu , Dan-Bo Zhang , Junchi Yan

Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-regularized regime unexplored. We study the learning curve and benign overfitting of…

Machine Learning · Statistics 2026-04-28 Weihao Lu , Qian Lin , Yingcun Xia , Dongming Huang

Background: It is still an open research area to theoretically understand why Deep Neural Networks (DNNs)---equipped with many more parameters than training data and trained by (stochastic) gradient-based methods---often achieve remarkably…

Machine Learning · Computer Science 2018-11-30 Zhiqin John Xu

In machine learning practice it is often useful to identify relevant input features. Isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we…

Machine Learning · Computer Science 2025-11-24 Lorenzo Chicchi , Lorenzo Buffoni , Diego Febbe , Lorenzo Giambagli , Raffaele Marino , Duccio Fanelli

In this article, we consider the problem of few-shot learning for classification. We assume a network trained for base categories with a large number of training examples, and we aim to add novel categories to it that have only a few, e.g.,…

Machine Learning · Computer Science 2020-03-23 Hong-Gyu Jung , Seong-Whan Lee

Training feedforward neural networks with standard logistic activations is considered difficult because of the intrinsic properties of these sigmoidal functions. This work aims at showing that these networks can be trained to achieve…

Neural and Evolutionary Computing · Computer Science 2017-10-04 Emanuele Sansone , Francesco G. B. De Natale

When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data. This "overfitting" is greatly reduced by randomly omitting half of the feature detectors on each training case.…

Neural and Evolutionary Computing · Computer Science 2012-07-04 Geoffrey E. Hinton , Nitish Srivastava , Alex Krizhevsky , Ilya Sutskever , Ruslan R. Salakhutdinov

Neural networks have achieved remarkable performance in various application domains. Nevertheless, a large number of weights in pre-trained deep neural networks prohibit them from being deployed on smartphones and embedded systems. It is…

Machine Learning · Computer Science 2023-07-19 Shibo Yao , Dantong Yu , Ioannis Koutis

One of the arguments to explain the success of deep learning is the powerful approximation capacity of deep neural networks. Such capacity is generally accompanied by the explosive growth of the number of parameters, which, in turn, leads…

Machine Learning · Computer Science 2022-09-15 Zuowei Shen , Haizhao Yang , Shijun Zhang