Research map / Learning theory and algorithms / Kernels and regression theory
Generalization Bounds for Canonicalization: A Comparative Study with Group Averaging
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 generalization bounds for canonicalization-based invariant/equivariant learning and compares them with group averaging.
Problem
Generalization capabilities of canonicalization, a method for producing invariant or equivariant function classes by projecting inputs onto a reduced subset before learning, remain underexplored compared with its expressive power and continuity.
Approach
Provides a theoretical generalization analysis of canonicalization and a comparative study against group averaging, based only on the abstract's framing (details not available).
Experimental setup
Baselines: group averaging
Builds on: canonicalization group averaging
Closest papers by meaning
- A Canonicalization Perspective on Invariant and Equivariant Learning (NeurIPS 2024 · similarity 0.91)
- Equivariant Frames and the Impossibility of Continuous Canonicalization (ICML 2024 · similarity 0.89)
- Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions (NeurIPS 2025 · similarity 0.84)
- LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization (NeurIPS 2024 · similarity 0.84)
- Generalizing across Temporal Domains with Koopman Operators (AAAI 2024 · similarity 0.84)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.83)
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.