SynthCore

Training ideas

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

2 ideas found

Status: Failed on benchmark Category: Training Math: Geometry Clear all
✗ Failed on benchmark 2026

Neural Surrogate for Worst-Case Barrier Drift

Distill the expensive inner minimization over state-estimation errors into a neural correction term that predicts the robust barrier drift, then fine-tune the correction using differentiable closed-loop rollouts. This retains the robustness mechanism while reducing the repeated optimization cost and allowing less conservative behavior than fixed analytic uncertainty bounds.

Useful8/10
Difficulty6/10
Novelty8/10
Training SpeedupStabilityAccuracy
Paper: Learning-Based Measurement-Robust Control Barrier Functions for Obstacle Avoidance under State Estimation Error arXiv:2608.20467
✗ Failed on benchmark 2026

Diffusion-DPP Gradient Batches

Replace uniform minibatch sampling by a fixed-size determinantal point process whose similarity matrix is a diffusion kernel on the training-data k-NN graph. The sampler repels nearby or redundant examples while preserving multiple diffusion modes, so a small batch should cover intrinsic data geometry and provide lower-variance estimates of losses and gradients.

Useful8/10
Difficulty6/10
Novelty5/10
Training AccuracySample efficiencyGeneralization
Paper: Fast determinantal sampling on general spaces and diffusion geometry arXiv:2607.06644