Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Learning to Generalize: An Information Perspective on Neural Processes
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 an information-theoretic framework that analyzes generalization bounds of Neural Processes, introducing a dynamic-dependent quantity (abstract truncated).
Problem
Existing Neural Processes are evaluated empirically and lack rigorous theoretical understanding of their generalization.
Approach
Uses an information-theoretic framework to derive generalization bounds for Neural Processes, introducing a dynamic-dependent quantity; the abstract is truncated so the full mechanism is not stated.
Closest papers by meaning
- Neural Processes with Stability (NeurIPS 2023 · similarity 0.91)
- Generalization at the Edge of Stability (NeurIPS 2026 · similarity 0.89)
- On the generalization of learning algorithms that do not converge (NeurIPS 2022 · similarity 0.89)
- Towards Generalization beyond Pointwise Learning: A Unified Information-theoretic Perspective (ICML 2024 · similarity 0.88)
- Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Power (ICLR 2025 · similarity 0.87)
- Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel (NeurIPS 2025 · 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.