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

Fantastic Four: Differentiable and Efficient Bounds on Singular Values of Convolution Layers

ICLR 2021 · Learning theory and algorithms › Kernels and regression theory · approach: Generalization theory of deep networks · 2 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Closest papers by meaning

• Norm-Based Generalisation Bounds for Deep Multi-Class Convolutional Neural Networks (AAAI 2021 · similarity 0.90)
• The Sample Complexity of One-Hidden-Layer Neural Networks (NeurIPS 2022 · similarity 0.89)
• Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration (ICML 2023 · similarity 0.88)
• Norm-based Generalization Bounds for Sparse Neural Networks (NeurIPS 2023 · similarity 0.87)
• Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks (ICML 2021 · similarity 0.87)
• Generalizable Adversarial Training via Spectral Normalization (ICLR 2019 · similarity 0.86)