English
Related papers

Related papers: Learning distinct features helps, provably

200 papers

For high-dimensional Gaussian data, we investigate theoretically how the features of a two-layer neural network adapt to the structure of the target function through a few large batch gradient descent steps, leading to an improvement in the…

Machine Learning · Statistics 2025-06-05 Yatin Dandi , Florent Krzakala , Bruno Loureiro , Luca Pesce , Ludovic Stephan

Neural networks often operate in the overparameterized regime, in which there are far more parameters than training samples, allowing the training data to be fit perfectly. That is, training the network effectively learns an interpolating…

Machine Learning · Computer Science 2025-03-19 Suzanna Parkinson , Greg Ongie , Rebecca Willett

Recently, a spate of papers have provided positive theoretical results for training over-parameterized neural networks (where the network size is larger than what is needed to achieve low error). The key insight is that with sufficient…

Machine Learning · Computer Science 2022-03-01 Gilad Yehudai , Ohad Shamir

The ability of learning useful features is one of the major advantages of neural networks. Although recent works show that neural network can operate in a neural tangent kernel (NTK) regime that does not allow feature learning, many works…

Machine Learning · Computer Science 2024-11-06 Mo Zhou , Rong Ge

Recent works have suggested that finite Bayesian neural networks may sometimes outperform their infinite cousins because finite networks can flexibly adapt their internal representations. However, our theoretical understanding of how the…

Machine Learning · Computer Science 2022-11-29 Jacob A. Zavatone-Veth , Abdulkadir Canatar , Benjamin S. Ruben , Cengiz Pehlevan

Attention layers -- which map a sequence of inputs to a sequence of outputs -- are core building blocks of the Transformer architecture which has achieved significant breakthroughs in modern artificial intelligence. This paper presents a…

Machine Learning · Computer Science 2023-07-24 Hengyu Fu , Tianyu Guo , Yu Bai , Song Mei

Neural networks may naturally favor distance-based representations, where smaller activations indicate closer proximity to learned prototypes. This contrasts with intensity-based approaches, which rely on activation magnitudes. To test this…

Machine Learning · Computer Science 2025-02-05 Alan Oursland

Ensembles of Convolutional neural networks have shown remarkable results in learning discriminative semantic features for image classification tasks. Though, the models in the ensemble often concentrate on similar regions in images. This…

Computer Vision and Pattern Recognition · Computer Science 2023-02-28 Tobias Schlagenhauf , Yiwen Lin , Benjamin Noack

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

In many networks, vertices have hidden attributes, or types, that are correlated with the networks topology. If the topology is known but these attributes are not, and if learning the attributes is costly, we need a method for choosing…

Machine Learning · Statistics 2010-05-25 Xiaoran Yan , Yaojia Zhu , Jean-Baptiste Rouquier , Cristopher Moore

Simplicity bias, the propensity of deep models to over-rely on simple features, has been identified as a potential reason for limited out-of-distribution generalization of neural networks (Shah et al., 2020). Despite the important…

Machine Learning · Statistics 2024-11-08 Nikita Tsoy , Nikola Konstantinov

Recently, there have been numerous studies on feature learning with neural networks, specifically on learning single- and multi-index models where the target is a function of a low-dimensional projection of the input. Prior works have shown…

Machine Learning · Statistics 2025-03-28 Alireza Mousavi-Hosseini , Adel Javanmard , Murat A. Erdogdu

The past decade has witnessed a successful application of deep learning to solving many challenging problems in machine learning and artificial intelligence. However, the loss functions of deep neural networks (especially nonlinear…

Machine Learning · Statistics 2017-10-23 Yi Zhou , Yingbin Liang

Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretical analysis on training two-layer ReLU neural networks in a…

Machine Learning · Statistics 2021-06-30 Shunta Akiyama , Taiji Suzuki

We consider the approximation of functions by 2-layer neural networks with a small number of hidden weights based on the squared loss and small datasets. Due to the highly non-convex energy landscape, gradient-based training often suffers…

Machine Learning · Computer Science 2025-08-14 Johannes Hertrich , Sebastian Neumayer

In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks. In particular, we first propose Minkowski difference based linear separability measures (MD-LSMs) to evaluate…

Machine Learning · Computer Science 2023-07-27 Chao Zhang , Xinyu Chen , Wensheng Li , Lixue Liu , Wei Wu , Dacheng Tao

Deep neural networks trained over large datasets learn features that are both generic to the whole dataset, and specific to individual classes in the dataset. Learned features tend towards generic in the lower layers and specific in the…

Machine Learning · Computer Science 2018-04-24 Edward Collier , Robert DiBiano , Supratik Mukhopadhyay

Deep neural networks (DNNs) defy the classical bias-variance trade-off: adding parameters to a DNN that interpolates its training data will typically improve its generalization performance. Explaining the mechanism behind this ``benign…

Machine Learning · Statistics 2023-05-02 Diego Doimo , Aldo Glielmo , Sebastian Goldt , Alessandro Laio

Modern neural network architectures for large-scale learning tasks have substantially higher model complexities, which makes understanding, visualizing and training these architectures difficult. Recent contributions to deep learning…

Machine Learning · Computer Science 2024-10-30 Jayadeva , Himanshu Pant , Mayank Sharma , Abhimanyu Dubey , Sumit Soman , Suraj Tripathi , Sai Guruju , Nihal Goalla

Neural networks have achieved remarkable empirical performance, while the current theoretical analysis is not adequate for understanding their success, e.g., the Neural Tangent Kernel approach fails to capture their key feature learning…

Machine Learning · Computer Science 2023-10-20 Zhenmei Shi , Junyi Wei , Yingyu Liang