Research map / Learning theory and algorithms / Kernels and regression theory

Generalization Bounds for Neural Networks with Sparse Connectivity

NeurIPS 2026 · Learning theory and algorithms › Kernels and regression theory · approach: Empirical generalization measures

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Derives non-asymptotic excess risk bounds for deep neural networks whose layer-wise weight matrices are sparse, showing how sparsity affects statistical generalization.

Problem

Existing generalization theory only partially explains how the pronounced sparsity of learned neural network solutions influences statistical performance.

Approach

Non-asymptotic excess risk bounds for deep networks with sparse layer-wise weight matrices, characterizing how sparsity enters the statistical rate.

Closest papers by meaning

• Generalization Bounds for Rank-sparse Neural Networks (NeurIPS 2025 · similarity 0.91)
• Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.90)
• Fantastic Generalization Measures are Nowhere to be Found (ICLR 2024 · similarity 0.90)
• Sharper Guarantees for Learning Neural Network Classifiers with Gradient Methods (ICLR 2025 · similarity 0.89)
• Slicing Mutual Information Generalization Bounds for Neural Networks (ICML 2024 · similarity 0.89)
• Generalization of Scaled Deep ResNets in the Mean-Field Regime (ICLR 2024 · similarity 0.88)