Training ideas

Curricula, sampling schedules, pseudo-labeling and multi-task mixing, with the standard training recipe as the control.

26 ideas found

Status: Mechanism failed Category: Training Clear all

✗ Mechanism failed 2026

Energy-Derived Nitsche Neural Fields

Represent a solution on an unfitted domain with local neural subnetworks and train them using one augmented energy containing the bulk physical energy, symmetric Nitsche boundary or interface terms, and a derivative-jump ghost penalty. Automatic differentiation of this scalar objective supplies all gradients and avoids independently tuning inconsistent PDE residual, flux, and boundary losses. The method is especially suited to moving geometries, cut-cell domains, and domain-decomposed neural…

Useful6/10

Difficulty5/10

Novelty6/10

Training Stability Accuracy Scalability

Paper: A Unified CutFEM Formulation for Finite-Strain Elasticity: Energy Minimisation and Corner Singularities arXiv:2607.02334

✗ Mechanism failed 2026

Constant-sum ordinal preference loss

Use a constant-sum point vector to encode ordered pairwise outcomes and train a neural scorer with an adjacent-categories ordinal likelihood whose slope parameters are tied to those points. The accumulated point score is then a theoretically motivated compressed statistic for repeated comparisons, rather than an arbitrary regression target or one-hot label.

Useful6/10

Difficulty4/10

Novelty6/10

Training Accuracy Sample efficiency Generalization

Paper: Ranking by points and ordinal models arXiv:2608.23859