Research map / Learning theory and algorithms / Sample complexity
Operator learning without the adjoint
Nicolas Boullé, Diana Halikias, Samuel E. Otto, Alex Townsend
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 |
|---|---|---|---|
| increase the convection coefficient c (greater non-self-adjointness) from 0 to 10 | Rational neural network Green's function learner · 1D convection-diffusion Green's function | relative error: plateau in relative error increases with c; error within 0.3-0.5% for c=0, 5, 10 | Hurt |
| increase the perturbation magnitude of the operator away from self-adjointness | Rational neural network Green's function learner · 1D convection-diffusion Green's function | relative L2 error: linear increase, R^2=0.78 | Hurt |
| test at higher grid resolution than training resolution (s=200 to up to 400) | Rational neural network Green's function learner · 1D convection-diffusion Green's function | relative error | No clear effect |
| increase number of training pairs beyond 10 | Rational neural network Green's function learner · 1D convection-diffusion Green's function | relative error: exponential decay up to 10 training pairs, then stagnation | No clear effect |
Closest papers by meaning
- On the Benefits of Active Data Collection in Operator Learning (ICML 2025 · similarity 0.85)
- Intrinsic-dimension empirical Bernstein inequalities for bounded self-adjoint operators (NeurIPS 2026 · similarity 0.84)
- Optimal deep learning of holomorphic operators between Banach spaces (NeurIPS 2024 · similarity 0.84)
- Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching (ICML 2025 · similarity 0.83)
- Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning (NeurIPS 2024 · similarity 0.83)
- Learning single index models via harmonic decomposition (NeurIPS 2025 · similarity 0.82)
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.
