paper-with-me

Papers

Learning with Shallow Neural Networks on Cluster-Structured Features

2026-05-14 · Elisabetta Cornacchia, Laurent Massoulié arxiv

The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While standard theoretical models typically assume that this structure lies in the target function, projecting unstructured inputs onto a low-dimensional subspace, data such as images, text or genomic sequences exhibit strong spatial correlations within the input space itself. In this paper, we propose a tractable model to study how these correlations affect the sample complexity of learning with gradient descent on shallow neural networks. Specifically, we consider targets that depend on a small number of latent Boolean variables, and input features grouped into clusters and correlated with the latent variables. Under an identifiability assumption, we show that for a layerwise gradient-descent variant, the sample complexity scales with the number of hidden variables and, when the signal-to-noise ratio is sufficiently high, is independent of the input dimension, up to logarithmic terms. We empirically test our theoretical findings on both synthetic and real data.

📄 PDF Abstract BibTeX arXiv:2605.14927

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Asymmetric double-winged multi-view clustering network for exploring Diverse and Consistent Information

2023-09-01 · Qun Zheng, Xihong Yang, Siwei Wang, Xinru An 외

In unsupervised scenarios, deep contrastive multi-view clustering (DCMVC) is becoming a hot research spot, which aims to mine the potential relationships between different views. Most existing DCMVC algorithms focus on e…

ClusteringDiversityPseudo Label

On the convergence of group-sparse autoencoders

2021-02-13 · Emmanouil Theodosis, Bahareh Tolooshams, Pranay Tankala, Abiy Tasissa 외

Recent approaches in the theoretical analysis of model-based deep learning architectures have studied the convergence of gradient descent in shallow ReLU networks that arise from generative models whose hidden layers are…

Clustering

Robust Multilingual Named Entity Recognition with Shallow Semi-Supervised Features

2017-01-31 · Rodrigo Agerri, German Rigau

We present a multilingual Named Entity Recognition approach based on a robust and general set of features across languages and datasets. Our system combines shallow local information with clustering semi-supervised featu…

ClusteringMultilingual Named Entity Recognitionnamed-entity-recognitionNamed Entity Recognition+1

The Rlign Algorithm for Enhanced Electrocardiogram Analysis through R-Peak Alignment for Explainable Classification and Clustering

2024-07-22 · Lucas Plagwitz, Lucas Bickmann, Michael Fujarski, Alexander Brenner 외

Electrocardiogram (ECG) recordings have long been vital in diagnosing different cardiac conditions. Recently, research in the field of automatic ECG processing using machine learning methods has gained importance, mainly…

Clustering

Quantum Feature Optimization for Enhanced Clustering of Blockchain Transaction Data

2025-05-22 · Yun-Cheng Tsai, Samuel Yen-Chi Chen

Blockchain transaction data exhibits high dimensionality, noise, and intricate feature entanglement, presenting significant challenges for traditional clustering algorithms. In this study, we conduct a comparative analys…

Clustering