A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization
arXiv:2608.23885
2026
Training
2 ideas extracted · analyzed Sep 1, 2026
What the math gives to ML
The paper identifies a practically important failure mechanism: low prediction error on historical trajectories does not preserve the economically relevant optimum of a dynamical process. Neural surrogate models can create multiple phantom optima, and stochastic gradient training can move from weights that recover the correct optimum to observationally similar weights with poor decision performance. The strongest transfer to neural networks is decision-oriented training and validation: explicitly test and regularize the surrogate's optimal-control landscape rather than relying only on trajectory fit.
Ideas from this paper
✗ Failed on benchmark
2026
Train a neural dynamical surrogate not only to reproduce measured trajectories, but also to reproduce the plant's economically optimal decision and objective value. Add a differentiable decision loss obtained by solving the surrogate's inner optimization problem, and reject models that fit observations while producing extra local optima or a shifted optimum.
Useful8/10
Difficulty6/10
Novelty7/10
✗ Failed on benchmark
2026
Treat the optimized surrogate and the training trajectory as objects that require a decision-level audit. Use multistart optimization to count phantom optima, and periodically evaluate whether stochastic training has changed the surrogate optimum even when validation prediction error remains nearly constant; stop, roll back, or average checkpoints when decision drift exceeds a threshold.
Useful7/10
Difficulty4/10
Novelty8/10