Research map / Learning theory and algorithms / Kernels and regression theory
On the Sample Complexity of Learning under Geometric Stability
Alberto Bietti, Luca Venturi, Joan Bruna
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use permutation-invariant kernel instead of cyclic or block-cyclic invariant kernels | KRR with arc-cosine dot-product kernel · synthetic permutation-invariant target, d=6 | estimation error |f_n - f*|^2 | Improved |
| use invariant kernel instead of non-invariant kernel with block size s=2 | KRR · synthetic block-cyclic target, d=12 | estimation error |f_n - f*|^2 | Improved |
| use invariant kernel instead of non-invariant kernel with block size s=6 | KRR · synthetic block-cyclic target, d=12 | estimation error |f_n - f*|^2 | Improved |
Closest papers by meaning
- The Exact Sample Complexity Gain from Invariances for Kernel Regression (NeurIPS 2023 · similarity 0.90)
- Sample Complexity Bounds for Estimating Probability Divergences under Invariances (ICML 2024 · similarity 0.89)
- Geometry and Stability of Supervised Learning Problems (JMLR 2025 · similarity 0.87)
- Learning with Exact Invariances in Polynomial Time (ICML 2025 · similarity 0.86)
- Optimal Sample Complexity of Contrastive Learning (ICLR 2024 · similarity 0.85)
- Stabilizing Sample Similarity in Representation via Mitigating Random Consistency (ICML 2025 · similarity 0.85)
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.
