Research map / Learning theory and algorithms / Sample complexity
On the Lipschitz Continuity of Set Aggregation Functions and Neural Networks for Sets
Giannis Nikolentzos, Konstantinos Skianis
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 mean instead of max aggregation under a single added outlier element (ablation) | set neural network · ModelNet40 Pert. #1 | average accuracy drop: 20.1 -> 2.0 | Improved |
| use max instead of mean aggregation under small noise on all elements (ablation) | set neural network · Polarity Pert. #2 | average accuracy drop: 13.6 -> 4.8 | Improved |
| larger Wasserstein distance between source and target cardinality bins | NN_mean and NN_max · Polarity size generalization | accuracy drop: r = 0.92 / 0.90 (small to large); r = 0.94 / 0.90 (large to small) | Hurt |
Closest papers by meaning
- Some Fundamental Aspects about Lipschitz Continuity of Neural Networks (ICLR 2024 · similarity 0.91)
- ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks (NeurIPS 2024 · similarity 0.90)
- Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks (NeurIPS 2019 · similarity 0.90)
- A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness (NeurIPS 2024 · similarity 0.87)
- Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations (ICLR 2024 · similarity 0.86)
- Approximation theory for 1-Lipschitz ResNets (NeurIPS 2025 · similarity 0.86)
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.
