Metamorphic testing of learned AC optimal power flow surrogates reveals representation dependence
cs.LG, cs.AI, cs.SY, eess.SY, math.OC
Submitted: 2026-11-10
Updated: 2026-11-10
Terminology
Sources
- CANOS: A Fast and Scalable Neural AC-OPF Solver Robust To N-1 Perturbations
- DC3: A learning method for optimization with hard constraints
- Relational inductive biases, deep learning, and graph networks
- Domain-Validity-Gated Metamorphic Testing of Scientific ML Surrogates
- LUMINA: Foundation Models for Topology Transferable ACOPF
- OPFData: Large-scale datasets for AC optimal power flow with topological perturbations
- The Power Grid Library for Benchmarking AC Optimal Power Flow Algorithms
- Frame Averaging for Invariant and Equivariant Network Design
- On the Stability of Expressive Positional Encodings for Graphs
- Deep Sets
- On the Benefits of Invariance in Neural Networks
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis