Research map / Architectures and efficiency / CNN design
Convolutional Spectral Kernel Learning with Generalization Guarantees (Abstract Reprint)
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.
Proposes convolutional spectral kernel learning to bring hierarchical and local feature learning from CNNs into kernel methods, aiming to improve kernel performance on complicated tasks.
Problem
Kernel methods are shallow and fully connected, so they fail to capture hierarchical features and local interdependencies and underperform CNNs on complicated tasks.
Approach
Incorporates convolutional structure into kernel methods (spectral kernel learning) so that kernels can acquire hierarchical and local knowledge, rather than remaining shallow fully connected models.
Closest papers by meaning
- End-to-End Kernel Learning with Supervised Convolutional Kernel Networks (NeurIPS 2016 · similarity 0.90)
- Automated Spectral Kernel Learning (AAAI 2020 · similarity 0.90)
- Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines (NeurIPS 2024 · similarity 0.89)
- Approximation and Learning with Deep Convolutional Models: a Kernel Perspective (ICLR 2022 · similarity 0.89)
- The Unreasonable Effectiveness of Patches in Deep Convolutional Kernels Methods (ICLR 2021 · similarity 0.89)
- HoloNets: Spectral Convolutions do extend to Directed Graphs (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.